Theoretically MediaInfinite AI Art Styles to Create! Check out Recraft’s newest features for free go.recraft.ai/theoreticallymedia_styles. Use my code MEDIA11 for $11 off any paid plan. Today we're diving deep into Recraft, the amazing AI image generation platform that just keeps getting better! Whether you're a Recraft newbie or a seasoned pro, this video is packed with goodies, as we're covering all their latest and greatest features – and trust me, some of this stuff is seriously cool.
I'll walk you through everything from Recraft's premier Recraft V3 model (you might remember it as Red Panda!) to its fantastic new capability to integrate external models like GPT-4, Flux, and Imagen. We'll explore the freedom of the infinite canvas (no confusing "murder boards" here, thankfully!), learn how to effortlessly switch up styles, edit images with precision, fine-tune those important details, and even use the creative upscaler for stunning results.
But wait, there's more! I'll also show you how to re-style your existing images, tap into Recraft's powerful vector art features, and explore the mind-blowing Infinite Styles engine. To really put it through its paces, I even took on a couple of fun projects: designing some unique album covers (shoutout to King Gizzard and the Lizard Wizard fans!) and creating a cool little mini-comic.
It's going to be a blast, so let's get crafting!
✨ HERE'S WHAT WE'LL COVER: ✨
00:00 - Welcome Back to Recraft! 00:46 - Meet Recraft V3 & External Model Power! 01:54 - Infinite Canvas, NOT a MurderBoard! 03:20 - Easy Styling, Editing & Fine-Tuning Your Art 05:15 - Upscaling & Re-Styling Your Images Like a Pro 06:14 - Unleash Your Inner Vector Artist with Recraft 06:50 - Creative Side Quest: Designing Album Art & Introducing Infinite Styles! 08:10 - Navigating the Endless Ocean of Styles in Recraft 09:01 - First Style Test: "Vibrant Retro Fresco" & More Cool Discoveries! 09:29 - The Real Magic: Creating YOUR OWN Unique Styles by Blending! 10:31 - Zazz Up Your Designs with Text & Logos 12:04 - Creating Mini-Comics & Unique Style Blends 13:42 - Why You Should Totally Try Recraft!
🚀 GET STARTED WITH RECRAFT & SAVE! 🚀 I've had an absolute blast making everything from comic books to album covers with Recraft, and I'm genuinely excited to see what you all create with it!
The good folks at Recraft have given me a coupon code to share with you! Use code MEDIA11 for $11 off any paid plan at checkout! Heads up: This video was made in partnership with Recraft. I only team up with brands and tools that I genuinely enjoy using and believe will bring you value too!
👍 LIKED THE VIDEO? LET ME KNOW!
Give this video a THUMBS UP if it sparked some creative ideas! COMMENT below – I'd love to hear what you're planning to create with Recraft! SUBSCRIBE to the channel for more deep dives into AI tools, creative software, and digital art adventures! Thanks so much for watching! My name is Tim.
Infinite Image Styles With This Unique AI Platform!Theoretically Media2025-05-28 | Infinite AI Art Styles to Create! Check out Recraft’s newest features for free go.recraft.ai/theoreticallymedia_styles. Use my code MEDIA11 for $11 off any paid plan. Today we're diving deep into Recraft, the amazing AI image generation platform that just keeps getting better! Whether you're a Recraft newbie or a seasoned pro, this video is packed with goodies, as we're covering all their latest and greatest features – and trust me, some of this stuff is seriously cool.
I'll walk you through everything from Recraft's premier Recraft V3 model (you might remember it as Red Panda!) to its fantastic new capability to integrate external models like GPT-4, Flux, and Imagen. We'll explore the freedom of the infinite canvas (no confusing "murder boards" here, thankfully!), learn how to effortlessly switch up styles, edit images with precision, fine-tune those important details, and even use the creative upscaler for stunning results.
But wait, there's more! I'll also show you how to re-style your existing images, tap into Recraft's powerful vector art features, and explore the mind-blowing Infinite Styles engine. To really put it through its paces, I even took on a couple of fun projects: designing some unique album covers (shoutout to King Gizzard and the Lizard Wizard fans!) and creating a cool little mini-comic.
It's going to be a blast, so let's get crafting!
✨ HERE'S WHAT WE'LL COVER: ✨
00:00 - Welcome Back to Recraft! 00:46 - Meet Recraft V3 & External Model Power! 01:54 - Infinite Canvas, NOT a MurderBoard! 03:20 - Easy Styling, Editing & Fine-Tuning Your Art 05:15 - Upscaling & Re-Styling Your Images Like a Pro 06:14 - Unleash Your Inner Vector Artist with Recraft 06:50 - Creative Side Quest: Designing Album Art & Introducing Infinite Styles! 08:10 - Navigating the Endless Ocean of Styles in Recraft 09:01 - First Style Test: "Vibrant Retro Fresco" & More Cool Discoveries! 09:29 - The Real Magic: Creating YOUR OWN Unique Styles by Blending! 10:31 - Zazz Up Your Designs with Text & Logos 12:04 - Creating Mini-Comics & Unique Style Blends 13:42 - Why You Should Totally Try Recraft!
🚀 GET STARTED WITH RECRAFT & SAVE! 🚀 I've had an absolute blast making everything from comic books to album covers with Recraft, and I'm genuinely excited to see what you all create with it!
The good folks at Recraft have given me a coupon code to share with you! Use code MEDIA11 for $11 off any paid plan at checkout! Heads up: This video was made in partnership with Recraft. I only team up with brands and tools that I genuinely enjoy using and believe will bring you value too!
👍 LIKED THE VIDEO? LET ME KNOW!
Give this video a THUMBS UP if it sparked some creative ideas! COMMENT below – I'd love to hear what you're planning to create with Recraft! SUBSCRIBE to the channel for more deep dives into AI tools, creative software, and digital art adventures! Thanks so much for watching! My name is Tim.Ultimate NanoBanana Deep Dive (Hacks, Tips, and Tricks You Need To Know!)Theoretically Media2025-08-28 | Is NanoBanana the most powerful image model we've ever seen? I've spent the last few days testing Gemini 2.5 Flash's image capabilities, and I've found some wild tips, tricks, and one crazy hack that completely solves the aspect ratio problem so many of you have mentioned!
In this deep dive, I'm skipping the basics and getting right into how to make this model do incredible things. We'll cover everything from a massive VEO 3 update that gives you unlimited fast generations to a powerful workflow that combines Nano Banana and VEO to create your own virtual movie sets. Plus, I'm breaking down the official Google prompting documentation so you don't have to!
00:00 - Intro: The Nano Banana Deep Dive 00:23 - My Fifth Banana Video! 00:50 - VEO 3 UPDATE: All-You-Can-Eat Generations! 01:19 - New VEO 3 Feature: Image Referencing 01:56 - Quality Check: Gemini UI vs. The API 02:38 - Where to Get The Best Results 02:56 - Using LM Arena (Free but with a Cooldown) 03:20 - The BIG Problem: Changing Aspect Ratios 03:42 - The Frame Hack Solution! 04:07 - Prompting 101: The Official Google Format 05:14 - Prompting 201: Don't Forget to Have Fun! 05:42 - Multi-Image Blending (The "Whisk" Feature) 06:16 - A BETTER Way to Blend: The Contact Sheet Trick 06:42- Is NanoBanana Perfect? 07:11 - NanoBanana on Recraft 08:50 - File Size in Nanobanana API vs Gemini 11:09 - Respecting the 180-Degree Rule 11:49 - How to ACTUALLY Rotate The Camera 12:11 - CRAZY WORKFLOW: VEO 3 + Nano Banana 12:40 - Creating Your Own Virtual Set 13:07 - Cinematic Test 14:01 - Please Subscribe for More! 14:14 - What's Coming Next
LINKS: My Previous NanoBanana Video: youtu.be/fJGSubH9SLs Gemini 2.5 Flash Image Docs: https://ai.google.dev/gemini-api/docs/image-generation#prompt-guide GEMINI: gemini.google.com/app LMARENA Direct Chat: lmarena.ai/?chat-modality=image&mode=directGoogles NanoBanana Image Powerhouse is Out & FREE!Theoretically Media2025-08-26 | Google just casually dropped the most powerful AI image editor we've seen, and the best part? It's basically everywhere, unlimited, and FREE! I've been covering "Nano Banana" since the start, so VERY EXCITED!
In this video, I’m diving into what makes Google's new Gemini 2.5 Flash Image so incredibly good. We'll cover the wild story behind its secret release, explore the conversational AI that powers its precise edits, and test it out across different platforms. From changing a dress color to completely changing the camera angle with a simple text prompt, this tool is a serious game-changer. Join me as we go completely bananas with this new AI photo editing model!
👇 Chapters 👇
00:00 – The Best FREE AI Image Editor is Here! 00:29 – The Secret Story of "Nano Banana" 01:09 – Why It's #1 in the World (Literally) 01:36 – How It Works: The Conversational AI Advantage 02:41 – Where to Use It (Hint: It's Everywhere!) 03:17 – The Free Playground You Need to Try 03:37 – My First Test Edits in Gemini 04:23 – Has It Been Nerfed? Arena vs. Gemini 05:05 – Putting Conversational Prompts to the Test 05:50 – Editing Real Photos (Amazing & Frustrating) 06:46 – Where This AI Model REALLY Shines 07:14 – You Can Argue With This AI?! 07:53 – Using External Platforms vs. Gemini 08:18 – The One Killer Feature ONLY in Gemini 08:43 – Final Thoughts & What's Coming Next
Try Gemini 2.5 Flash Image (Direct Chat) LLARENA: lmarena.ai/?chat-modality=image&mode=directKlings Frames Are Insane & MORE Nano Banana!Theoretically Media2025-08-25 | Kling's new "First Frame, Last Frame" feature is finally here for the 2.1 model, and I can honestly say it's the best version we've seen yet! I’ve been experimenting with it, and in this video, I'm diving deep into what makes it so impressive.
We're going to look at some of my own experiments—from aging Keanu Reeves to creating some dynamic, Blade Runner-inspired scenes—to see where this feature truly shines and where it still has a few quirks. Plus, I put together a short narrative film to test its storytelling capabilities using the viral "Nano Banana" model.
And speaking of bananas, we've got some exciting community findings and a potential release date for the mysterious model that everyone's talking about. Stick around to the end as we also break down the huge news about Midjourney's new partnership with Meta!
CHAPTERS 00:00 – Kling 2.1's New Feature is Rolling Out! 00:12 – What We're Covering Today 01:10 – First Experiment: Aging Keanu Reeves 01:36 – Second Experiment: Keanu as Constantine 02:16 – Promptless Test: Ana de Armas in the Wick Verse 02:39 – Adding a Prompt for a Special Effect 02:49 – Testing Prompt Adherence: Blade Runner Skyline 03:31 – Prompting vs. No Prompt: Hong Kong Action Cinema 04:14 – Can It Work for Narrative? (Short Film Showcase) 05:11 – Analysis: What Went Wrong With My Short Film 05:47 – The Ongoing Problem with Chaining Frames 06:33 – Community Highlight 06:44 – Community Highlight 07:03 – Community Highlight 07:27 – We Need to Talk About Nano Banana 07:49 – PSA: How to Use Nano Banana (For Free!) 08:18 – Nano Banana Release Date Rumors 08:49 – The Power of Nano Banana: Community Tests 09:36 – Huge News: Midjourney & Meta Partnership 09:58 – What This Partnership Actually Means for Users 10:57 – What Do You Think About "Meta Journey"? 11:01 – Final Thoughts & Outro
LINKS: LM Battle Arena: lmarena.ai/?chat-modality=image Previous video on NanoBanana: youtu.be/JLX7x854Xq0Fresh Nano Banana News & 3 Big Runway Updates!Theoretically Media2025-08-21 | This week, the creative AI world has been buzzing about one thing: Nano Banana! In this video, I’m pulling back the curtain on the most powerful AI image tool I have ever seen. We’ll dive into how it’s making its debut on the new Pixel 10, when it’s coming to YOUR phone, and I'll even show you my own mind-blowing experiments that prove just how revolutionary this technology is.
And if that wasn't enough... Runway just partnered with Google.
Yes, you heard that right. You can now generate V3 video directly inside the Runway platform. I'll show you how to access it, what it costs, and how this historic collaboration creates the ultimate AI toolkit for creators.
Strap in. This is a big one.
Thanks To Teachable for Sponsoring Today's Video: Hit the link for a FREE 30 day Extended Trial: rebrand.ly/theoretically-media
🕒 EXPLORE THE FUTURE: 00:00 — The Secret AI Everyone's Talking About 00:52 — CONFIRMED: The Banana is Google! 01:34 — Your First Look at "Gem-Pix" on Pixel 10 02:02 - Any Other Doubts 02:40 - Banana In Whisk 03:12 — The Ultimate AI Workflow: Nano Banana + Google Flow 03:48 - Nano Banana on iOS and Android 04:19 — The Only Way to Access Nano Banana Right Now 04:33- Nano Banana Is Amazing 05:10 - My own Spin 05:59 - Vintage Photo in Nano Banana 06:52 - Beware of Fake Bananas 07:19 - Veo-3 In Gemini Mobile? Wait...what? 08:06 - A Word From Teachable 10:27 — Runway's New A-List Voice Cloner 10:47 - Act 2 Voice Change Walkthrough 11:41- Changing the Voice 12:01 - Who are these Voices? Elevenlabs?! 12:44 — THE BIG ONE: Runway + Google V3 is HERE 13:17 - The Man in the Green Tuxedo 13:35- Aleph Meet Veo-3! 14:40 — Is the Runway Unlimited Plan a Veo Cheat Code? 15:43 — Go Play Runway!
🔗 TOOLS & RESOURCES:
My Original Nano Banana Investigation: youtu.be/JLX7x854Xq0 Runway Act-2: youtu.be/Ni_6i3LSBcQ Runway Game Worlds Video: youtu.be/Q53iqEq78Acs Jump into Runway's Game Worlds: play.runwayml.com/loginNano Banana & Qwen: The New KINGS! Try them FREE!Theoretically Media2025-08-19 | I'm diving into two brand new AI image editors that you can test out for FREE right now. One of them, a mysterious tool called Nano Banana, is seriously one of the most impressive I've ever seen. Plus, we'll cover some quick updates from Kling and a cool new video-to-audio feature from Eleven Labs that you'll definitely want to try. UPDATE with the latest Nano Banana News: youtu.be/v2Do9jyWi4I
I'm back from vacation and excited to jump back into the world of AI with you! We're kicking things off with a look at a new open-source model from Alibaba called Quinn, and then we'll get to the mysterious and powerful Nano Banana that has the community buzzing with speculation about it being a Google project. I'll walk you through my own tests with both, from changing guns to bananas to creating hyper-stylized anime images and even generating new camera angles for a scene.
My thanks to Notion for Sponsoring today's video: Get Started with Notion AI at: https://ntn.so/TheoreticallyAIFW
00:00 - Introduction to New AI Image Editors 00:53 - Exploring Alibaba's Qwen Image Editor 01:18 - Testing Qwen 01:57 - Qwen vs GPT Image 02:20 - Qwen's Editing Capabilities 03:09 - Real-World Tests with Qwen 03:47 - Black and White to Color 04:17 - The Model's two streams 04:30 - Impressive Features of Qwen 05:16 - Qwen's Strengths and Weaknesses 05:48 - Lean into what it is good at 06:26 - The Mysterious Nano Banana 06:56 - It is Impressive 07:08 - How to Try Nano Banana for Free 07:28 - Voting with Nano Banana 08:04 - Generating New Camera Angles 08:48 - Shot Scene Created 09:02 - Nano Banana and Real-Life Photography 09:26 - Results 10:05 - No Face Scrambling 10:26 - Style Consistency 10:44 - So What IS Nano Banana?! 11:32 - Using Notion for AI Film Production and Creative! 16:31 - Kling AI Update 16:54 - Kling First Last in Action 17:26 - Eleven Labs' New Video-to-Music Feature 18:41 - Final Thoughts
LINKS: Qwen Chat: chat.qwen.ai LM Battle Arena: lmarena.ai/?chat-modality=imageTwitters Video Model is CRAZY (and FREE for now!)Theoretically Media2025-08-07 | Get ready for a deep dive into the most talked-about AI updates! We're putting X's controversial Grok video model to the test to see if it's as unhinged as the headlines claim. Is Midjourney's new HD video worth the high price tag? We'll compare the results and the cost. Plus, we're exploring the brand-new Eleven Labs music generator and its capabilities with vocals and instrumentals. Discover a free AI video platform, Morphic, with a surprisingly powerful 3D feature and co-pilot mode. To round it all out, we get a first look at the promising new image model from Leonardo AI.
0:00 - Intro 0:46 - X's Grok Video Model 1:30 - Grok Video Demo & Features 2:21 - Grok Video with Sound 3:01 - Grok's "Fun Mode" 3:29 - Image-to-Video with Grok 03:55 - Side note on Image to Video 4:16 - The "Spicy" Controversy 5:00 - Taylor Swift gets Spicy 5:45 - Grok Tightening Up 6:12 - Vine and the Future of Grok 6:55 - Creative Uses for Grok 7:16 - Midjourney HD Video 7:40 - How Much of a difference is HD? 8:05 - Is Midjourney HD Worth It? 08:52 - In Good Midjourney News... 9:06 - Eleven Labs Music Generator 09:15 - Pirate Time! 09:47- Let's Get Funky! 10:13 - Eleven Labs Music Workflow 10:47 - New Sections and Limitations 11:04 Editing Audio 11:33 - Morphic 3D Video 12:29 - 3d Result 12:40 - Morphic's Impressive Co-Pilot 13:19 - Second Test 13:45 - Try out Morphic 13:58 - Leonardo's New Image Model 14:04 - Producer AI Tips 14:58 - No Future, putting the Punk in Cyberpunk! 15:29 - Producer AI Vocal Retake! 16:22 - Chat with you song? 16:51- Producer writes a new section 17:45 - Leonardo's new Image Model 18:01 - Playing Around with Leo 18:22 - Mayorking Outputs 19:01 - Admin notes!
LINKS: Grok - https://x.ai/ Midjourney: midjourney.com/explore?tab=hot Topaz: topazlabs.com/ref/2518 ElevenLabs: https://elevenlabs.io?utm=check Morphic: morphic.com Leonardo: https://app.leonardo.ai?via=timGoogles Genie 3 is Veo-3s Endgame!Theoretically Media2025-08-05 | You won't believe what Google just unleashed! In this video, I'm diving deep into Genie 3, a groundbreaking AI that's set to revolutionize everything we know about video, gaming, and even our path to AGI. Forget everything you thought was possible, because this new technology is creating fully interactive, photorealistic worlds from a single image or prompt. I'll break down how Genie 3 works, what it means for the future of interactive entertainment, and when you might actually get your hands on it.
From one-second playable games in its first version to mind-blowing, controllable video, I've been following the Genie project from the very beginning. In this video, we'll explore the incredible leap to Genie 3, which combines the best of past versions with the physics understanding of Veo to create something truly special. We're talking about generating entire environments you can walk around in, with object permanence that lasts for minutes!
Join me as I break down the craziest examples, from painting a wall in a controllable video to adding a chicken-suit-wearing runner to a POV London walk. This isn't just about making cool videos; it's a major step towards creating truly intelligent systems.
Here’s what we’ll cover:
00:00 – Google’s AI Bombshell is Here 00:28 – The Evolution of Genie: From 1 to 3 01:18 – The Secret Sauce: Merging Genie & Veo 01:42 - Bashing Genie 3 and Veo-3 02:14 – A New Level of Fidelity: Genie 3 vs Genie 2 02:50 - New Environments with Genie 3 03:12 – Beyond Games: Interactive, Controllable Video 03:49 – Solving AI's Biggest Problem: The Memory Test 04:10 - The Classroom Example 04:38 – How It Builds Worlds From Scratch 05:06 – Choose Your Own Adventure: Prompting New Realities 05:42 - The London Walking Scene 06:13 - Dragons and Jet Skies 06:38 – Incredible Physics & Light Interaction 07:10 - Can it drive VR? 07:47 – The AGI Connection: Meet Sima, The AI Agent 08:09 - Agents in Action! 08:47 – Is AI Lucid Dreaming? The Path to AGI 09:23 - What can it do today? 09:50 – The Bad News: When Can You Use It? 10:14 - But it might be coming! 10:35 - This is the Worst It Will Be
What are your thoughts on Genie 3? Is this the future of gaming and interactive media? Let me know in the comments below! And if you enjoy deep dives into the latest AI tech, be sure to like this video and subscribe to the channel for more updates.The Future of AI Music Generation has LandedTheoretically Media2025-08-01 | Get ready to meet the new boss of AI music generation... who's actually the old boss! In this video, I'm taking a first look at Producer AI, the evolution of the OG AI music tool, Riffusion. It’s got a whole new conversational workflow that feels like you're co-writing with an AI, and I'm diving in to see what it can do.
From creating a summer pop anthem to generating a modern country song about hating modern country, we're putting Producer AI to the test across a bunch of genres. We'll even explore its hip-hop capabilities and make a stoner rock track inspired by Black Sabbath. I'll walk you through the new features like the "Add Vibe" option, direct recording, and how you can customize the AI to your creative process.
Join me as we explore the future of music creation!
CHAPTERS: 00:00 – Introduction to the "New" AI 00:24 – First Look at Producer AI 01:04 – Generating a Summer Pop Song 01:26 - Melting Point 02:32 – The Modern Country Test 03:32 - Country Song Urban Refrain 03:57 – Creating Album Art & Looping Videos 04:21 – Making a Relatable Hip-Hop Anthem 04:38 - Nothing On, the Trap Anthem 05:21 – Using the "Add Vibe" Feature 05:40 - Finding Inspiration With a Playlist 06:36 – A Metal Tribute to Ozzy 06:50 - A Brief History of Stoner Rock 07:25 - The Madman Howls 08:01 – Editing & Customizing Your Tracks 08:11 - Additional Producer Functions 08:42 – Recording Guitar Directly into the AI 09:15 -Dreampop with Direct Recording 09:39 - Producer works on the Dreampop song 10:21 - Using it as Backing Tracks for Practice 11:06 - Downloading Stems 11:18 – What's Next 11:42 - Final Thoughts and Pricing
LET'S CONNECT! What features do you want to see in AI music generators? Let me know in the comments below! And if you enjoyed this look at the cutting edge of music tech, be sure to like, subscribe, and hit that notification bell so you don't miss what's next.Runways AI Video Bombshell!Theoretically Media2025-07-30 | Runway has just unleashed a game-changer in the world of AI video, and I’m here to break it all down for you. This new feature, codenamed "Aleph," is taking video editing to a whole new level, whether you're working with AI-generated content or traditionally captured footage. Is this the end of the VFX industry as we know it? Not quite, but it's an incredibly powerful tool that you'll want to see in action.
In this video, I'm putting Runway's new model through its paces. We'll be doing everything from changing the color of a tuxedo in a Midjourney creation to colorizing classic black and white stock footage. I'll even show you how I gave a static shot a brand-new wide-angle perspective! We'll also have some fun with its multimodal capabilities by adding a pair of Midjourney-designed sunglasses to a character in a scene from Casino Royale. Plus, you won't want to miss how this tool can seamlessly remove unwanted elements from your videos, whether it's distracting subtitles or even the main characters.
I'll also be showcasing some incredible creations from the community, including a mind-bending reverse angle of the Joker and a full VFX treatment for a barbarian queen who was originally shot on a green screen. We'll even explore how this new technology can be used as a powerful rendering engine.
So, get ready to have your mind blown and join me as we explore the exciting new frontier of AI-powered video creation!
Chapters: 00:00 – Runway's AI Video Bombshell! 00:46 - The New Workflow is Agentic? 01:03 – Testing AI on a Midjourney Video 01:41 - Traditional Video Testing 02:01 – The 5-Second Limit & Creative Workarounds 02:18 - Expanding Shots 03:01 – Character Consistency: A Clockwork Orange Test 03:16 - Prompting, be a good manager! 03:44 – Multimodal Bond 04:10 - The Joker 04:40 - Green Screen Barbarian Queen Test 05:00 – The Office Removal 05:21 - Removal from Veo-3 Footage 05:54 - Removing Veo-3 Subtitles 06:21 – Visual Prompt Removal 06:42 - Prompting Tips Again 07:13 - The Sweeney Test! 07:30 – Community Showcase Begins! 08:03– Real-World Footage 08:32 - The Matrix Reimagined 08:53 - Outtakes and the Fun of it All 09:31 – Wan 2.2 and Ideogram's updates 09:49 - News from Showrunner
If you enjoyed this video, don't forget to HIT that LIKE button, LEAVE a COMMENT with your thoughts, and SUBSCRIBE for more explorations into the latest in AI technology!
Thanks for tuning in!VEO-3 has a Secret Super Power!Theoretically Media2025-07-28 | Ready to dive into a mind-bending new Veo-3 hack? I’m exploring a fresh technique for AI VIdeo called "visual prompting," where you can scribble directly on your images to control your AI Video Shots. We'll find out if this method gives us more creative power than just using text prompts. Plus, stick around as we check out Runway's latest game-changer: a new in-context video model called Olive that is seriously impressive!
In this video, I'm putting this cool visual prompting workflow through its paces. The core idea is to overlay text annotations and drawings on your input image, giving Veo specific instructions on what to animate and where. I’m running a bunch of my own experiments, from creating epic dragon battles and controlling camera movements to making an alien wormhole appear out of thin air. We’ll see what works, what doesn't, and I'll even show you how you can use free tools like Adobe Express to get started.
We'll also jump over to the latest from Runway and their new "Aleph" feature. Think of it as in-painting on steroids! It's a cutting-edge in-context video model that lets you perform video-to-video edits, transfer styles, and even remove objects seamlessly. While it’s not available to everyone just yet, I’ll give you a sneak peek at its incredible potential and why I believe it will be a huge asset for both AI-generated content and your everyday videos.
WHAT WE COVER: 00:00 - Intro: The New "Visual Prompting" Hack 01:11 - Tools for Visual Prompting (Canva, Adobe Express) 02:13 - Test #1: Directing an Epic Dragon Battle 03:12 - Test #2: Advanced Camera Control Experiments 04:17 - Test #3: Steampunk Zeppelin & Sequential Actions 05:06 - Test #4: Cyberpunk 180-Degree Camera Test 05:45 - Sidney Sweeny's Karate Moves 06:22 - Test #5: Spicing it Up with Kaiju Chaos! 07:11 - Test #6: Combining In-Painting & Reference Images 08:06 - Test #7: Animating Dialogue with Speech Bubbles 09:03 - Is Visual Prompting a Game-Changer? My Verdict 09:57 - Introducing Runway's New Model: Aleph 10:36 - Aleph's Capabilities: Style Transfer & Shot Generation 11:18 - Aleph's Secret Weapon: Video Object Removal 12:10 - What's Next & Thank You!
Thanks for tuning in! It’s shaping up to be a busy week, so if you had fun with this one, don't forget to like, comment, and subscribe to stay updated on all the cool stuff coming up.Veo-3s Wild Debate & Klings NEW Feature Will SHOCK You!Theoretically Media2025-07-24 | Ever wondered if you're using the best prompting strategy for Veo-3? This week, we're diving deep into the spirited debate between text and JSON prompting to see if one truly comes out on top. I'll share some tips and tricks along the way to help you get the most out of your creations.
But that's not all! I've got a first look at a brand-new workflow from Kling called Kling Lab that you won't want to miss. We'll round things out with some exciting news from Midjourney, including updates on video generation and their upcoming API.
chapters 00:00 - Intro 00:26 - Quick Vo three Updates 01:14 - What is JSON Prompting? 02:07 - Json in Action 02:57 - Control vs. Efficiency in Prompts 03:55 - The Case for Natural Language 04:41 - Test 1: Text vs. JSON (The Man in the Green Tuxedo) 05:57 - Test 2: 70s Crime Vibe Comparison 06:50 - Test 3: Abstract Prompts (T.S. Eliot's The Wasteland) 08:12 - Image-to-Video Showdown (The Bunker Scene) 09:27 - A Good Veo-3 Tip 09:58 - When JSON Goes Wrong (The Country Music Detective) 11:12 - A Cool JSON Prompting "Hack" 11:39 - The Hack in Action 12:17 - Final Verdict: Is There a Best Method? 12:44 - A word from Teachable 15:28 - First Look: Kling Lab's New Node Workflow 16:03- The UI 16:33 - Additional New Features 18:18 - Exciting Midjourney Video Updates 19:12 - A Fun Midjourney Trick
LETS CONNECT What's your take on text versus JSON prompting? Have you found more success with one over the other? Let me know your thoughts and experiences in the comments below! And if you enjoyed this deep dive, don't forget to like, subscribe, and hit that notification bell so you don't miss out on future content. Thanks for watching!GPU Poor? Try This for Uncensored Open Source AI Video & Images!Theoretically Media2025-07-18 | Ever wanted to dive into the world of open-source AI Video without dropping a fortune on a high-end GPU? I get it, the hardware costs can be a major roadblock. But what if I told you there's a way to harness the power of top-tier GPUs for a fraction of the cost? In this video, I'm showing you exactly how to do that! We'll be walking through the process of renting a powerful GPU and using it to generate and edit AI images and videos with tools like Flux and Wan. And trust me, if I can do this, you can too!
I used to think Comfy UI was a beast to tackle, but I discovered a secret: you don't have to be an expert to use it. We'll be using pre-made templates that make the process super simple. Think of it like driving a car without needing to know how to build one. We'll cover everything from setting up your accounts on Runpod, Hugging Face, and Civitai to deploying your first model and creating some awesome AI content. Plus, I'll show you how to get those shots that other platforms might block. So, if you're ready to unlock the full potential of open-source AI, let's get started!
CHAPTERS 00:00 – Intro: The Three Camps of AI Creation 00:52 – A Smarter Way to Access Powerful GPUs 01:30 – Getting Started with Runpod, Hugging Face, and Civitai 02:18 – Renting Your First GPU 03:01 – Exploring Community Workflows in Runpod 03:23 - Here's where you might get scared... 03:38 – Don't Be Scared! 04:31 - Make some scratch with Runpod 04:49 - Picking a GPU 07:49 - Depoying Your GPU 05:13 – Setting Up Your Image Generation Template 08:10 – Generating Your First AI Images with Flux 10:33 – Editing Images with the Kontext Workflow 11:17 – Generating AI Video with Wan 14:45 – The Power of Image-to-Video 15:48 – Why Open Source Matters
If you found this video helpful, be sure to hit that like button, leave a comment with your creations, and subscribe for more AI tutorials! Let me know what you think of this workflow in the comments below!Runways NEW Update is an AI Video Gamechanger!Theoretically Media2025-07-16 | Check out Spotter Studio here: https://sptr.la/theoretically Runway just dropped an AI Video banger, and I’ve already spent my morning putting their new Act Two feature to the test! I was so excited that I created an entire short film in just about three hours to see what it could really do.
In this video, I’m giving you a first look at Runway’s new performance capture tool. We're going to break down what it's great at, what it's not so great at, and all the lessons I learned along the way. From animating Orson Welles to dealing with some wonky shots and discovering the importance of head orientation, I'm sharing my entire creative process. Plus, we'll take a look at some mind-blowing examples from the creative community!
CHAPTERS
00:00 – Runway's New Banger: Act Two! 00:24 – A Note on the Early Beta 00:36 – Runway's Growing Arsenal of Tools 00:53 – My "War of the Worlds" Short Film 03:31 – Post-Film Reaction & Production Time 03:50 – Let's Break It Down: Accessing Act Two 04:11 – Uploading an Image vs. Using Your Webcam 04:40 – First Test: Surprising AI Storytelling 04:58 – The Background Comes Alive! 05:07 – Animating Orson Welles with References 05:40 – The Problem with Video Length 05:53 – The Misery of Lip-Syncing 06:18 – AI Bugs Out: Decoherence & Morphing 06:31 – The Head Orientation Breakthrough 06:54 – Generating the Scene & Characters 07:34 – Combining Characters in a Single Shot 07:52 – Pro Tip: Directing the AI's Focus 08:07 – Matching My Performance to the AI 08:32 – The Final Audio Workflow (feat. ElevenLabs) 08:50 – Essential Settings: Expressiveness & Gestures 09:09 – When Glitches Become Narrative 09:31 – The Gratification of Performance Capture 09:57 – A Word From Our Spotter Studio 14:19 – Testing Different Aspect Ratios 14:37 – Tip for Better Hands: The Pirate Test 15:15 – Eleanor's "Man Hands" Issue 15:31 – What Act Two is REALLY For 15:51 – Combining Dialog Shots with AI Action 16:15 – Community Spotlight: The Real Robot Dale 16:24 – Community Spotlight: Purz's Puppets 16:42 – It Even Works for Animals! 16:55 – Community Spotlight: Using Props with Timmy 16:59 – Community Spotlight: AI Warper's Comparison 17:13 – Final Thoughts & What's Next for Act Two
RESOURCES & LINKS
If you're interested in learning ComfyUI, you have to check out Purrs's channel: youtube.com/@PurzBeats
A huge thanks to our sponsor, Spotter Studio! You can find out more about them here: https://sptr.la/theoretically
Thanks for watching, and don't forget to like, comment, and subscribe for more deep dives into the latest creative tech. My name is Tim, and I can't wait to see what you create!This AI Video Restyle is Super Powered!Theoretically Media2025-07-14 | Today I'm tackling a bunch of exciting new AI tools that have been on my to-do list, and you won’t want to miss what I’ve discovered! We’ll be exploring a game-changing video-to-video restyler from Mago that nails some of the biggest challenges we've faced, like lip-syncing. Plus, we're taking a look at HiggsField's new character consistency feature and a surprisingly useful "non-creative" AI image upscaler from Magnific. It’s a packed episode, so let’s get into it!
In this video, I’ll show you: How Mago is leading the pack with its latest video-to-video updates. A hands-on tutorial for using Mago’s new timeline and control net features. My experience with Higgs Field's new character training feature, along with some helpful tips. A look at Magnific's non-creative AI image upscaler and why it's a game-changer.
CHAPTERS
00:00 - Introduction 00:56 - Problems with Video to Video 01:14 - Mago's Video-to-Video Restyler 01:29 - Once Upon a Time in the West Test 02:23 - How to Use Mago 02:50 - Restyle First Frame 03:04 - Mago Settings and Options 04:32 - Results 04:47 - Advanced Mago Techniques 05:41 - 1917 Test 06:50 - Severence Test 07:23 - An Amusing Experiment 08:10 - The Starship Troopers Test 09:27 - Exploring Higgs Field 09:39 - Exploring Soul 10:23 - Character Consistency in Higgsfield 10:51 - Training Data Bleed 12:00 - More Bleed, but Good Images 12:21 - Editing in Higgsfield 13:09 - From Image to Video with Higgs Field 13:50 - Impressive example from 8bit_e 14:40 - Magnific's Non-Creative AI Upscaler 15:42 - Final Thoughts
RESOURCES
Sign up for the Mago Beta Waitlist: https://www.mago.studio/ Check out HiggsField: higgsfield.ai Try Magnific's AI Upscaler: magnific.ai
If you enjoyed this video, don't forget to LIKE, COMMENT, and SUBSCRIBE for more AI explorations. Let me know in the comments which of these tools you're most excited to try!Veo-3 Gets a BIG Upgrade & Moonvalley First Look!Theoretically Media2025-07-08 | Get ready for a massive AI video update! Google's VEO-3 just dropped image-to-video with audio, and I'm diving deep into what it can do. We'll explore its strengths, weaknesses, and a pricing update you won't want to miss. Plus, I’ve got a first look at a brand new AI video generator called MoonValley, which is aimed squarely at the pros. You might be surprised to learn we’ve seen a much older version of it on this channel before!
In this video, I'll walk you through how to get the most out of VEO three's new features, including some tips and tricks to get you started. We’ll also take a deep dive into MoonValley, a powerful new tool for professional creators that's built on a clean, copyright-free model. From text-to-video and image-to-video to some seriously impressive video-to-video capabilities, there's a lot to unpack.
WHAT'S INSIDE: 00:00 - Intro 00:34 - VEO Three's Image-to-Video with Audio is Here! 00:53 - Operation Fuzzy Bunny: The Movie 01:33 - Veo-3 Pushback 02:06 - How to Use Frames to Video in VEO-3 02:49 - Veo-3 Fast vs Quality 04:00 - Fuzzy Bunny Generation Cost 04:49 - Quick Veo-3 Tip 05:17- Flamethrower Girl 05:43 - Creating Consistent Voices with VEO Three 06:16 - My Free VEO Three Prompt Builder! 06:50 - Veo-3 Action Scenes 07:22 - The Midjourney Version 07:44- Veo-3 Pricing Update 08:25 - Introducing Moon Valley: AI Video for Professionals 08:48 - Moonvalley from 2023?! 09:06 - Moonvalley 2023 Example 09:28 - Moonvalley Today 09:49 - Moonvalley Text to Video 10:18 - Moonvalley Image to Video 11:14 - Exploring Moon Valley's Video-to-Video Features 12:19 - How Many Keyframes?! 13:00 - The Future of AI Filmmaking 13:45 - More Controls incoming! 14:25 - Final Thoughts & What's Next
I'm incredibly excited about the potential of these new AI tools and what they mean for the future of filmmaking. What do you think? Let me know in the comments below!
If you enjoyed this deep dive into the latest in AI video generation, be sure to like this video, subscribe to the channel, and hit that notification bell for more content like this. Thanks for watching!GTA AI Is Here & WILD! (And You Can Play It!)Theoretically Media2025-07-04 | Get ready to explore the future of gaming because AI Grand Theft Auto is officially here, and you can play it right now—even before GTA 6! In this video, I'm taking a deep dive into the world of real-time AI world generation with a hands-on look at an incredible new generative AI game called 'Mirage'. This isn't just a tech demo; it's a playable, AI-powered game that serves as a massive benchmark for what's coming next in interactive entertainment, and it's wild.
We'll check out "Mirage" from Dynamics Lab, a game created entirely by AI in real-time. It’s not perfect, but the technology behind it is mind-blowing. We're talking frame-by-frame video generation that you can control with text prompts!
Get ready to see how we can take a game that looks like an old GTA title and transform it with a simple text command. Plus, I'll show you how you can even upload an image and generate your own game world.
IN THIS VIDEO:
00:00 - AI GTA is REAL! 00:36 - Welcome to Mirage: The AI Game Generator 01:11 - The Tech Behind The Game 01:25 Not Just GTA? 01:39 - What is the Tech Behind This? 02:25 - How Playable is it? 03:32 - The Game Might be a bit Empty 03:53 - You Can Text Prompt In the Game 04:17 - The Forza AI Experience 05:11 - Let’s Change The Game with a Text Prompt! 06:00 - Creating Your OWN Game World 06:40 - The Limitations of AI Gaming 7:00 - Spicing this up with Current Tech 07:13 - Using Text to Video 07:40 - Using Image to Video 07:52 - Impressive Results 08:12 - The Future of AI Game Rendering 08:55 - The Witcher Remastered 09:16 - Creative Video Upscaling 09:50 - Solving Object Permanence 10:33 - Google Has Been Quiet...too quiet 10:58 - The Future of Story and Characters in AI Games 11:30 - What This Means for Game Developers and Players 12:20 - What This Means If You're Just a Player of Games
This is just the beginning, and it’s pointing towards a future where we can create and play any game we can imagine. What kind of game would you create? Let me know in the comments below!
And if you enjoyed this look into the future of gaming, don't forget to like, subscribe, and hit that notification bell so you don't miss what's next!
Video On Genie 2: youtu.be/dFhzMEnCEhY Video On Runway Game World: youtu.be/Q53iqEq78AcThis AI Tool Remembers (& Discovers) For You!Theoretically Media2025-07-03 | Are you constantly drowning in a sea of articles, videos, and podcasts? I know I am! Keeping up with the rapid pace of new information, especially in the tech world, can feel impossible. Our old-school organizational methods just aren't cutting it anymore. That's why I've been on the hunt for a better solution and I think I’ve found something pretty cool.
In this video, I'm taking you on a tour of Recall, an AI-powered knowledge base designed to help you capture, connect, and retain information like never before. I'll show you how I'm using it to manage the chaos and turn information overload into a superpower. We're going to dive into its core features, check out the handy Chrome extension, and explore the mind-bending knowledge graph that reveals surprising connections in your research.
Let's get organized!
CHAPTERS: 00:00 – The Struggle is Real: Information Overload 01:08 – What is Recall? 02:44 – A Look at the Main Platform & Auto-Categorization 03:26 – Creating & Summarizing New Cards 04:15 – The Super-Handy Chrome Extension 05:35 – It Works with Arc Browser Too! 06:28 – The Magic of the Interconnected Knowledge Graph 08:28 – NEW Feature: Augmented Browse 09:38 – Taking Your Knowledge On-The-Go with the Mobile App 10:08 – Quiz Yourself to Retain More! 10:42 – Final Thoughts & How to Try Recall
▶ TRY RECALL & GET A DISCOUNT! Give Recall a shot and see if it clicks for you with their free tier. If you love it, use my special code for a discount on the paid version!
Use code: TM25 for 25% off a subscription Recall that is valid until 1 August 2025
▶ WHAT WE COVERED: Feeling overwhelmed by the constant stream of new information. How traditional organizational systems are falling short. An introduction to Recall, an AI tool for building a personal knowledge base. Capturing and summarizing anything from articles and YouTube videos to PDFs. Using the Chrome Extension for seamless capturing. Discovering hidden connections between topics with the knowledge graph. Exploring the new "Augmented Browse" feature that works locally on your device. Staying organized on the go with the mobile app.
I'd love to hear what you think of Recall in the comments below! What tools are you using to manage information overload?
As always, thanks for watching!AI Film Scripts Just Got REALLY Good!Theoretically Media2025-07-01 | Ready to write an Oscar-worthy screenplay... with a little help from AI? I’m taking a deep dive into PlotDot Horizon, the 2.0 version of the AI-powered screenwriting platform I first checked out back in 2023. A lot has changed since then, and I’m revisiting an old idea, "Overnight Delivery," to see if this tool can really turn a concept into a compelling script.
From brainstorming loglines and developing characters with surprising depth to structuring the entire plot, I’ll walk you through the whole process. We’ll see how PlotDot handles everything from character creation (with some hilarious hiccups) to generating a full-length screenplay. Is it perfect? Not yet. But it’s a massive leap forward and a powerful tool for any writer looking to get their first draft done in record time.
Join me as I explore whether AI is the future of screenwriting and how you can use these tools to bring your own stories to life!
In This Video: 00:00 – Introduction: AI Screenwriting Gets an Upgrade 00:20 – What is PlotDot? 00:56 – Looking Back: PlotDot in 2023 02:18 – The Idea: "Overnight Delivery" 04:07 – Brainstorming and Character Creation 06:48 – Structuring the Plot 07:56 – Writing the Screenplay with AI 09:33 – Is AI the End of Screenwriters? 10:51 – Bonus: Generating a Scene with Veo-3 12:03 – Final Thoughts
Resources Mentioned:
Check out PlotDot Horizon (currently in beta!): plotdot.ai/en
I hope you enjoyed this look into the future of screenwriting! Let me know in the comments what you think. Would you use AI to write a script?
Don't forget to LIKE, SUBSCRIBE, and hit that notification bell so you don't miss our next adventure into the world of AI creativity!
Thanks for watching! TimRunways Game Worlds is a Storytelling BEAST!Theoretically Media2025-06-27 | Ready player one? Runway just dropped an AI Game Engine, and it’s a total game-changer for generative AI and storytelling. In this video, I’m diving deep into Runway’s new "Game World" feature, showing you how to create your own text-based adventures and exploring the incredible potential it holds for creating simulated realities. Plus, we'll take a look at the latest updates to Runway's references feature!
I’ll walk you through everything from creating a character to navigating the game, and even show you how to build your own from scratch. We'll explore some wild scenarios, like the "Overnight Delivery" game I made where you have to survive a monster outbreak in a warehouse while keeping up with package orders! We'll also see how you can push the boundaries of the AI to create truly unique and unexpected storylines.
Get ready to explore the future of interactive storytelling!
In this video, you'll find:
00:00 – Introduction to Runway's Game Engine 00:35 - World Simulation Surprise 00:55 - What Exactly Is It? 01:19 – Exploring Pre-Made Games 01:33 - Starting a Game 02:05 - City of Ash 02:28 – A Closer Look at "The Last City of Ash" 02:54 - Inventory and Health 03:14 – Pushing the Limits of the AI 03:51 - UI and a Smart GM 04:41 – Image Generation in Game Worlds 05:17 - Asking for Images 05:53 - Is it Too Easy? 06:24 – Creating Your Own Game World 06:48 - Creating Overnight Delivery 07:24 - I'm not good at my own game 08:02 – Creative Storytelling Examples 08:58 – Naysaying and Expectations 09:20 - Current Developments in AI Open Worlds 10:18 - Where is Runway Headed With This? 10:42 – Making Films from Games 11:34- Updates to References 12:31 – Final Thoughts
What kind of game will you create with Runway's Game World? Let me know in the comments below! And if you enjoyed this video, don't forget to like, subscribe, and hit that notification bell for more adventures in AI.Stunning NEW AI Video & Real Time Voice To Video!Theoretically Media2025-06-25 | Check out Recraft for $11 Off Any Plan/mo: go.recraft.ai/media11 The new AI video model, SeeDance, is finally here, and it was worth the wait! In this video, I'm putting it through its paces and the good news is, it hits that sweet spot of being fast, cheap, and good. Plus, I’ve got a look at some mind-bending real-time voice-controlled AI video that you won't want to miss.
We're diving deep into SeeDance, the new AI video model from ByteDance. After a chaotic rollout with some initial bugs, SeeDance Pro is now widely available and working like a charm. I'll be testing it out on Krea, and I have to say, their new image model is pretty impressive too!
I'll walk you through my experiments with text-to-video and where I think this model really shines: image-to-video. We’ll look at everything from creating cinematic scenes to kung fu fights and some surprisingly good character acting and emoting. Plus, I'll reveal SeeDance's superpower that lets you create some really interesting cuts in your videos.
Later in the video, we'll check out Dream Stream for some real-time, voice-controlled AI video generation that's a lot of fun to play with. And a big thanks to Recraft for sponsoring this video and offering a sweet discount for you all!
RECRAFT PROMO CODE: MEDIA11 ($11 Off Any Plan for One Month) Or, just hit the link: go.recraft.ai/media11
00:00 - Introduction 00:41 - Admin Note 00:54 - Meet SeeDance: The New AI Video Model 01:25 - Problems at Launch 01:57 - Text-to-Video Tests Begin 02:49 - Text To Video Gets Better 03:06 - JSON Prompting works 03:41 - Image-to-Video: Where Sea Dance Shines 04:27 - Ten Second Generations 04:46 - Really Nice Filmic Looks 05:09 - The Kung Fu Test 06:12 - Seedance as a Camera Operator 06:47 - Dark Monster Locked Down Shot 07:13 - Acting and Emoting 07:29 - SeeDance's Superpower 08:11 - Is It Perfect? It Is Not. 08:53 - Pricing and the Fog of War 09:39 - Recraft & Prompt Editing 10:19 - Kontext Max Hair Dye Job 11:19 - Kontext For Image Editing 11:58 - GPT Text Editing For AI Comics Rocks! 13:29 - Recraft Coupon Code! 13:51 - Real-Time Voice-Controlled AI with Dream Stream 14:02- Dreamstream Real Time Demo 15:06 - Where this is Cool 15:22 - Hardware? 15:44 -Warpy Creative Upscaling with Topaz AstraDid Midjourney Video Cook? The Ultimate Review!Theoretically Media2025-06-19 | It's hard to believe, but Midjourney video is finally here, and it's seriously impressive! I’ve been putting it to the test and I’m ready to share my thoughts on where it soars and where it stumbles.
In this video, I’m taking a deep dive into Midjourney's new video capabilities. We'll explore everything from its low-cost, low-resolution approach to some mind-blowing stylized outputs that you won't want to miss. I’ll also share some cool tips and tricks I've discovered along the way, including how to get the most out of your generations without burning through your fast hours.
Plus, I’ve got an exclusive first look at the new creative video upscaler from Topaz, called Astra. It’s the perfect companion for Midjourney’s low-res videos, and the results are pretty stunning.
If you’re as excited as I am about the future of AI video, you’re in the right place!
CHAPTERS:
00:00 – Introduction to Midjourney Video 00:31 - A Few Sticky Points 00:52 – First Look: Las Vegas Wedding Chapel 01:24 - A Note On Upscaling 01:55 - First Test Woman in a Red Dress 02:34 – Manual Mode & The Runaway Bride 03:18 – Midjourney's Surprisingly Great Hands 03:40 - Prompting in old images 04:09 – Impressive Character Movement & Emoting 04:52 - Really great movement 05:09 – Kung Fu Fight Sequence Test 05:30 - The Road to Vengeance 05:46 - Background details 06:19 - Background Characters with our Orc Queen 06:42 - Adding elements with extensions 07:10 – Stylized & Animated Outputs 08:09 – Stylistic Consistency Showcase 09:18 – Testing with Midjourney V4 & V5 09:31 - The Sneering King 09:59 - Conan 10:08 - Argento style v4 10:34 - V4 Love 10:44 – Midjourney Pushback & Limitations 11:48 - Famous Faces 12:00 – Tips, Tricks & A 360 Rotation Hack 13:04- Verdict on Midjourney Video 13:36 – First Look at Topaz Astra Creative Upscaler 14:25 - The Sneering King Upscaled 14:47 - The Cyberpunk Pirate Upscaled 15:25 - The Dumbest Knight Upscaled 15:39 - Some Problem Spots 15:57 - Can we get a Spicy Mode? 16:22 - Final Thoughts
RESOURCES MENTIONED:
► Sign up for the Topaz Astra Beta Waitlist: topazlabs.com/astra-earlyaccessMinimax 2.0 ROARS with the LOWEST $$ In AI Video?!Theoretically Media2025-06-17 | Hailuo MiniMax is back with its highly anticipated 2.0 update, and it's looking seriously impressive. In this video, I'll dive deep into my own tests to see what this new model is capable of, showcase some amazing community creations, and break down the all-important cost. Is this the VEO-3 killer we've been waiting for? Let's find out!
I'll be putting MiniMax 2.0 through its paces, comparing it to the previous version and other AI video generators out there. From text-to-video and image-to-video tests to recreating iconic movie scenes, I’m leaving no stone unturned. You won't want to miss my final verdict on whether it's worth your time and money.
Hop over To Hailou to Try It Out: https://preview.hailuoai.video?invite-code=72718084
In this video:
00:00 – Introduction 00:33 - The Long Wait 01:10 – The New Model 01:30 - What Does the New Model Have? 01:58 - Voices Like Veo-3? No. But... 02:48 – Man in the Blue Suit Test 03:43 – Creating New and Novel Things 04:31 - Summoning a Fire Demon 04:51 - The 10 Second Shots 05:29 – Text-to-Video vs. Image-to-Video 06:07 – New Model vs. Old Model 06:52 - Testing Director Mode 07:21 - Panning New Vs Old 07:51 – Fight Scene Test 08:36 – Recreating a Classic Movie Scene 09:20 - Quick shots 09:46 – Community Creations 11:45 – The Cost
I'm really excited about what MiniMax 2.0 brings to the table, especially with its director mode capabilities and improved coherence. While it's not perfect, the advancements are significant, and the creative potential is huge.
What are your thoughts on the new Mini Max 2.0? Let me know in the comments below if you'd like to see a shootout between the major AI video generators! And if you enjoyed this video, don't forget to like, subscribe, and hit that notification bell for more AI video content.Midjourney VIDEO & LAWSUIT! Plus: FREE Krea! Topaz, & MORE!Theoretically Media2025-06-12 | Midjourney has dropped some massive news, and in this video, I'm breaking down the good, the bad, and the downright awesome, starting with our very first look at their much-anticipated AI video model. This isn't just another update; it's a potential game-changer for generative AI and AI art. I've already ranked over 500 clips to give you a sneak peek!
But that’s not all. We're covering the whole landscape of AI image generator and video tools. I'm diving into the major copyright lawsuit Midjourney is facing from Disney and Universal , a cool new chat editing mode from Runway AI , and an incredible (and free!) AI image model from Krea AI that you have to see. Plus, I'll explore the Topaz Astra creative video upscaler and the new ByteDance Seedream video model. It's a packed week, so let's get right into it!
WHAT'S INSIDE:
00:00 – Introduction - Big news from Midjourney 00:38 – First Look at Midjourney Video 01:43 – The Midjourney Aesthetic 02:54 – Cinematic & Realistic Outputs 04:03 – 360 Rotations & Camera Movement 05:00 – Tech Specs & Limitations 07:44 – The Disney & Universal Lawsuit 09:01 – Runway's New Chat Mode 09:52 – Krea's FREE AI Image Model 13:15 – Topaz Labs' Creative Video Upscaler 14:31 – ByteDance's Seedream Model 15:16 – It's going to be a wild summer for AI!
Topaz Astra Waitlist: topazlabs.com/astra-earlyaccess Midjourney: midjourney.com Runway: runwayml.com Krea: krea.ai Dreamina (Bytedance): dreamina.capcut.comVEO-3 Is Now Cheaper, Faster, & Good?!Theoretically Media2025-06-09 | I'm diving deep into Google's newly released Veo-3 "Fast Mode" Is it possible to have fast, cheap, and good AI Video? I put it to the test with an A/B comparison against the "Big Daddy" quality mode, and the results might just surprise you. I'll also break down the cost, share an interesting prompt formula, and reveal a huge hack you won't want to miss!
00:00 – Introduction to Veo-3 Fast Mode 00:43 – Understanding the Speed and Cost 01:07 – Veo-3 presents Twin Peaks: Fast Mode in Action 02:05 – A/B Comparison: Fast Mode vs. Big Daddy Mode 02:22 - The Fallout Test - Veo3 Quality 02:55 - The Fallout Test - Veo3 Fast 03:28 – Bond-Inspired Veo-3 Fast vs Quality 04:19 - Preference to Fast? 04:40 – Game of Thrones Scene & Quality vs. Fast 05:39 – The Cost Breakdown: Fast Mode vs. Quality 06:28 – Prompts for Veo-3 06:52- JSON Prompting in Veo-3 07:35 - The Veo-3 JSON and Text Prompt Builder 08:30 – Character Retention Hack (Quality Mode) 09:08 - Character Test 2 09:27 - Tips for Character Retention and a Warning 10:17 – Kitbashing with Luma's Modify Feature 10:50 - The Result 11:11 – Final Thoughts & Google's Progress
Don't forget to like this video, leave a comment with your thoughts on Veo Fast Mode, and subscribe for more AI video creation content!
Stay tuned for the latest Veo updates! Thanks for watching!Reimagine Any Video With Luma AI’s Modify!Theoretically Media2025-06-05 | Luma Labs just dropped their new "Modify Video" feature, and you know I had to jump in and see what it's all about! As a huge fan of video-to-video workflows, I was super excited to take this for a spin. While this is more of a first look than a deep dive, I stumbled upon some cool tips and tricks that you'll definitely want to see.
In this video, I’m taking you through my initial experiments with Luma's "Modify Video." We're going to see how it handles restyling input videos, what happens when you use text prompts versus style frames, and I'll even show you some of my happy accidents along the way. I’m also going to test it out on some pre-existing footage, from classic films to old-school animated shows, to really push the limits of this new tool.
So, if you're curious about the future of AI video and want to see what Luma's new feature can do, you're in the right place. Let's get into it!
Chapters:
00:00 - Introduction to Luma's Modify Video 00:36 - The Evolution of AI Video Stylization 01:20 - Creative Examples and Props 02:35 - Testing with Pre-existing Assets 03:20 - Restyle and Upscale 03:51 - The Power of a Style Frame 04:38 - Results 05:02 - Where it isn't Great 05:45 - Experiments with Classic Film Footage 06:06 - Leone Goes Cyberpunk Western! 07:01 - And...where it isn't Great 07:37 - The Starship Troopers Test 08:23 - The Results 09:05 - Limitations and Problem Spots 09:25 - Running Test 09:57 - The Godzilla Test 10:28 - The Severance Test 11:18 - Things get Weird 11:44 - The "Doubling Up" Technique 12:35- Doubling Godzilla 12:59 - Pirate Gal Goes Depp! 13:40 - Awesome Community Examples 14:41 - Final Thoughts & Is It Worth It?
I had a ton of fun playing around with this new tool, and I think you'll have a blast seeing what it's capable of. If you enjoyed this video, make sure to hit that like button, leave a comment with your thoughts, and subscribe for more AI video adventures!AI Avatars Level Up BIG!Theoretically Media2025-06-03 | AI avatars have seriously leveled up, leading to that classic question: am I real, or am I an AI avatar? Spoilers... five fingers mean I'm real! But today, we're diving into the latest in AI avatar generation – and trust me, it's pretty wild. Plus, I've got a spot where you can try some of this magic out for FREE!
In this video, I'm checking out some mind-blowing new AI tools and updates. We'll explore how Black Forest Labs' "Kontext" is shaking things up with Flux news, take a peek at Topaz's new creative AI image upscaler which I'm super excited about, and even see how Sora is now kinda... sorta... free (with an asterisk, of course!). It’s a packed one!
00:00 - Intro: Real or AI Avatar? 00:18 - What's New in AI? (Big Updates!) 01:00 - AI Avatars Get a Major Upgrade: HeyJen, Hunan & The Impressive Mirage Studios! 01:27 - Hands-On: Trying Out Mirage Studios AI Avatars (Yes, There's a Free Trial!) 02:19 - Mirage Deep Dive: Uploading Audio, AI Voices & My First Avatar Test 03:06 - The Nitty-Gritty of Mirage: Those Tricky Sliders & Generating My Digital Twin! 03:37 - First Test 04:05- Second Test 04:35 - Third Test 04:45 - Fourth Test 05:06- Fifth Test 05:33 - My Thoughts on Mirage: The Good, The Jump Cuts & Let's Talk Price 06:33 - Exploring Black Forest Labs' "Context" on Leonardo.ai (Sponsored Segment!) 07:14 - Editing Like a Pro with Context & Flux: Changing Backgrounds, Adding Elements & More! 07:32- Man in a Blue Business Suit 08:19 - What I'm Most Impressed With 08:51 - Our Gal! 09:26 - Lights on, Lights Off! 10:16 - Even More Leonardo.ai Power: Checking Out Their Upscaler & Video Generation Tools 10:39 - Motion Controls 11:10 - Motion and Kontext and an Old School Mac 11:48 - Topaz Bloom Enters the Ring: A Look at Their New Creative AI Image Upscaling (Beta Access) 12:34 - Testing Bloom 13:22 - Test 2 14:06 - Our Gal...again! 15:31 - Is It Perfect? You know the answer! 16:29 - Wait, Sora is "Free" Now? Here’s the Catch & How You Can Try It!
I was genuinely impressed by some of these tools, especially how you can now try out an AI avatar generator like Mirage Studios from Captions for free to make content for TikTok, YouTube Shorts, or Instagram Reels! We'll also see how Leonardo.ai is integrating the powerful "Context" editor, allowing for some insane image manipulation like changing time of day or adding characters seamlessly. And I can't forget Topaz Bloom, which takes image upscaling to a whole new creative level.
If you're into AI, content creation, or just love seeing what's next in tech, you don't want to miss this one!
👍 Like this video if you found it helpful or entertaining! 💬 Comment below: Which AI tool are you most excited to try? 🔔 Subscribe and hit the bell so you don’t miss out on more AI adventures! 🔗 Share this video with a friend who needs to see these crazy AI updates! Thanks for watching, and I'll catch you in the next one to see what other wild AI news drops! My name is Tim.The 10 BEST AI Image Generators!Theoretically Media2025-05-29 | The 10 Best AI Image Generators! Try Zapier for free and start automating your work in minutes: bit.ly/4iXqXjz Ever find yourself asking, "What IS the absolute best AI image generator out there?" It's one of the top questions I see, and today, we're tackling it – but with a unique spin that I think you'll find way more useful than just another top ten list!
In this video, I'm diving into a bunch of the leading AI image generators, but instead of just ranking them, I’m giving you the lowdown on what makes each one special, its unique strengths, where it might have a few quirks, and who I think it's perfect for. From Midjourney's artistic flair to Ideogram's text prowess, and the new powerhouses like Flux and Runway's Frames, we're covering a LOT of ground.
00:00 - The Quest for the "Best" AI Image Generator 00:22 - A Word From My Awesome Sponsor: Zapier! 00:58 - The Most Influential Image Generator 03:08 - The One With A Ton Of Controls 04:43 - The One That References the best 06:24 - The One that Chats the Most! 08:20 - Quick Break: How Zapier Frees Up Your Creative Time! 09:20 - The King of Text 11:13 - The Commercially Safe One 12:41 - The Open Source One (And where to use it) 14:46 - The Zen-like One 16:15 - The One for Designers 16:58 - The New Kid on the Block 17:39 - So, Which One IS the Best? My Final Thoughts!
🚀 TOOLS & RESOURCES MENTIONED: 🚀
Zapier: Start automating your repetitive tasks for FREE and free up your creative time! Sign up here: bit.ly/4iXqXjz
(Pricing and specific features for each platform are discussed in their respective chapters!)
👍 WHAT'S YOUR GO-TO IMAGE GENERATOR?
LIKE this video if you discovered a new tool to try! COMMENT below and let me know YOUR favorite AI image generator, or your personal top list! SUBSCRIBE for more AI explorations, tool reviews, and creative adventures! Thanks again to Zapier for sponsoring this video and helping us all find more time to create!
As always, thanks for watching! My name is Tim.KLING 2.1! Does It Challenge Veo-3s Throne?Theoretically Media2025-05-27 | Today, we've got a HUGE update from Kling – they are dropping version 2.1 of their AI video model, and I've got a preview! With VEO 3 making waves, the big question is: has a worthy challenger appeared? Well, in this video, I'm breaking down everything Kling 2.1 has to offer, from its strengths and weaknesses to how it stacks up against the competition, especially in cost and output quality.
I'll be taking you through a bunch of examples, comparing Kling 2.0 with 2.1, and, of course, pitting Kling 2.1 against VEO 3 in a text-to-video and image-to-video shootout! Plus, I've got some news on VEO 3 pricing that you won't want to miss. So, buckle up as we explore if Kling 2.1 challenges the new king of AI video generation!
Here’s what I’m covering in this video:
00:00 – Intro: Kling 2.1 Preview! 00:41 – AI Video Heats Up: Kling 2.1 Enters the Ring 01:06 – Kling 2.1: What's New? (Early Access & Features) 01:33 – Head-to-Head: Kling 2.0 vs 2.1 Image-to-Video Examples 02:31 - Not Megan Fox With a Flamethrower 03:25 – Kling 2.1 Performance: Control, Quirks, and Epic Battles 03:46 - Vouge Output 04:21 - Model Handoff at 5 Seconds? 04:53 - Improved Textures 05:27 - Walk Cycles 05:49 - Fight Scenes Text to Video 06:11 – Community Creations: You Guys Are Awesome! 07:18 – Kling 2.1 vs. VEO 3: The Text-to-Video Tussle 07:51 - Not Cloverfield Back to Back 08:13- Game Of Thrones Ending Redux 08:57 – Kling's Strong Suit: Image-to-Video Deep Dive 09:17 - Kling's Natural Movement 10:07 - Prompt Pushback 10:46 – Our Pirate Gal: Aspect Ratios & Stylized Looks 11:30 - Animated Looks Are A No-Go in Veo 12:08 – The Price of Pixels: Kling 2.1 & VEO 3 Costs Explained 12:41 – Wrapping Up: My Thoughts & Future of AI Video
For Partnerships/Brand Inquires: tim@smoothmedia.coI Paid For Veo-3. Is It Worth It?Theoretically Media2025-05-22 | So, Google just dropped Veo 3, their new AI Video Generator, and it feels like we're stepping into the 3.0 era for this tech! Alongside Veo, they've launched Flow, a seriously impressive platform that brings together image, audio, and video creation. But hold onto your hats, because it comes with a hefty $250/month price tag! Is it worth it? Well, I decided to pony up the cash to find out for you!
In this video, I'm diving deep into Veo 3 and the Flow platform. We'll explore what it's amazing at, where it's still lacking, and ultimately, I'll let you know if you should "get into the Flow"! I'm checking out everything from its new ability to generate talking characters and create specific visual styles, to how it handles subtitles and compares with its predecessor, V2. We'll also look at some fun community creations and the often hilarious world of AI-improvised dialogue!
Here’s what I’m covering:
00:00 – Intro: Google Veo 3 & Flow Arrives! 00:44 – Veo 3 Can Talk! AI Man-on-the-Street Interviews 01:36 – 90s Sitcom Vibes & Style Capture 02:13 - Community Outputs 02:40 - My Favorite "We Can Talk" 02:55 – Veo 2 vs. Veo 3: Is There a Big Leap? 04:21 – Why Text-to-Video is Still King with Veo 3 04:37 - Text Vs Image Prompting In Veo-3 05:37 - Zapping Subtitles 06:38 – Fun Discoveries: Prompting Topics & Even Music! 07:28 – "The Jank" - Where Veo 3 Still Stumbles (Hello, Fight Scenes!) 08:43 - AI Sound can be FUN 09:28 – Playing with IP: Can Veo 3 Handle Fan Films? (The Mandalorian, Batman, John Wick style) 11:11 – The Downsides: What’s Missing from Veo 3 Right Now? 11:45 - Extensions Work, Kinda? 13:17 – The Elephant in the Room: Let's Talk Price 14:58 – My Final Thoughts & Should YOU Subscribe?
What do YOU think? Is this the future of AI video? Are you tempted to try it out despite the cost? Let me know your thoughts in the comments below! 👇
And if you found this helpful, don't forget to LIKE 👍, SUBSCRIBE 🔔, and SHARE this video!
Want to share your feedback with Google? 🔗 Google Labs Discord: discord.gg/googlelabs
Thanks for watching, and I'll catch you in the next one! My name is Tim.
For Partnerships/Brand Inquires: tim@smoothmedia.coGoogles AI Bombshells! Veo-3 and Flow CRUSHED it!Theoretically Media2025-05-20 | Google's annual I/O event just wrapped up, and let me tell you, they absolutely COOKED! I'm diving into all the juicy creative generative AI announcements they dropped, and spoiler alert: it's a feast! From mind-blowing video generation with Veo 3 to incredible image updates with Imagen 4, and a brand new platform called Flow that brings it all together, there's a TON to unpack.
In this video, I'm focusing on the creative AI goodness, but I'll also touch on some other cool things like Google Beam, the impressive new AI Search capabilities I've been testing, and the latest Gemini updates that are aiming to be a Siri that actually works! So, grab a snack, and let's check out the menu Google served up!
📖 Chapters:
00:00 – Did Google Cook? 00:39 – Quick Bytes: Google Beam & AI Search! 02:01 – Gemini Gets Personal! 03:28 – The Main Course: Creative AI! 03:31 – Imagen 4 04:42 – Lyria & the Music AI Sandbox! 05:23 – Veo 3 Unleashed: Next-Level Video! 07:01 – Veo 3's Character & Element Control! 07:22 – Wait, Veo 3 Does WHAT?! Sound & Dialogue! 08:39 – Introducing Flow: The All-in-One AI Creative Hub! 10:29 – Show Me the Money: Availability & Pricing! 11:16 – My Testing Plan & Your Requests! 11:37 – P.S. Google Sent Me a Shirt! I'm seriously impressed with what Google brought to the table this year, especially with Veo 3 and the Flow platform. It feels like the creative AI space is evolving at lightning speed!
I'll be doing a full run-through of Flow with Veo 3 later this week, so make sure you hit that LIKE and SUBSCRIBE button to see it in action (and help me subsidize these crazy AI costs! 😉).
And let me know in the COMMENTS below: What do you think of these announcements? Is there anything specific you want me to test out with Veo 3 or Flow?
Thanks for watching, and keep an eye out for that deep dive! My name is Tim.
give me the chapter section again, level back a little on those descriptions
Y Youtube Description Custom Gem
Show thinking Okay, here's the chapter section again with slightly more concise descriptions:
📖 Chapters:
00:00 – Did Google Cook? My initial thoughts on the I/O announcements and if Google delivered.
00:39 – Quick Bytes: Google Beam & AI Search! A brief look at the Google Beam 3D communication tool and the evolution of AI in Google Search.
02:01 – Gemini Gets Personal! Exploring Gemini's new personalization features for a true AI assistant experience and how it's aiming to be a more effective voice assistant.
03:28 – The Main Course: Creative AI! Diving into what Google announced for creative video, image, and audio generation.
03:31 – Imagen 4: Upping the Image Game! Details on the Imagen 4 update, focusing on image quality, detail, and speed enhancements.
04:42 – Lyria & the Music AI Sandbox! Updates to the Lyria music generation model and the new Music AI Sandbox for experimentation.
05:23 – Veo 3 Unleashed: Next-Level Video! Introducing Veo 3 with greater realism, 4K output, and new creative video features like camera controls and frame extension.
07:01 – Veo 3's Character & Element Control! How Veo 3 handles consistent characters and locations using driving video or image inputs.
07:22 – Wait, Veo 3 Does WHAT?! Sound & Dialogue! Exploring Veo 3's groundbreaking ability to generate sound effects and synchronized dialogue directly from prompts.
08:39 – Introducing Flow: The All-in-One AI Creative Hub! An overview of the new Flow platform, designed to integrate Imagen 4, Veo, and other tools for a seamless creative workflow.
10:29 – Show Me the Money: Availability & Pricing! A breakdown of the Google AI Pro and AI Ultra plans for accessing these new generative AI tools, including Veo 3.
11:16 – My Testing Plan & Your Requests! My plan to test Veo 3 and Flow, and an invitation for viewer suggestions.
11:37 – P.S. Google Sent Me a Shirt! A quick thank you to Google for the unexpected gift.
Sources
Gemini can make mistakes, so double-check itBlazing Open Source AI Video, Veo-3, and AI Script to Storyboard!Theoretically Media2025-05-15 | AI Video Goes Wild! Try out Spotter Studio for 7 days for FREE at my link: https://sptr.la/theoretically
Get ready for an action-packed update in the world of creative AI! In this video, I'm giving you the inside scoop on all the latest breakthroughs, from cutting-edge open-source projects to exciting developments from the big players. We'll dive into new models from LTX Video and Wan 2.1, check in on Midjourney and Runway, and even explore an intriguing script-to-storyboard platform. Trust me, you won't want to miss these game-changing advancements!
What's New in Creative AI? 00:00 – Introduction: Kicking things off with a quick rundown of all the exciting AI news I'm covering today. 00:19 – LTX New Distilled Model 01:05 - LTX Requirements 01:39 - LTX Multi-Scale Rendering 02:03 - Running LTX on Hugging Face 02:30- SUPER fast on LTX Platform 03:00 – Wan 2.1 VACE 03:14 - What is VACE? 03:41- What can VACE Do? 04:07 - This is Impressive! 05:19 - Wan 2.1 VACE Requirements 05:44 – Hunyuan's New Image Model 06:06 – Google's VEO3 & Imagen 4! 07:04 - Spotter Studio 09:34 – Script-to-Storyboard 11:32 – Storyboard Nuances 12:12 – Feedback for Rubber Band 12:46 – Midjourney's Omni Reference Update 13:57 – Runway's Act Two? 14:21 - Act-1 Clip From The Interview 14:56 - What might Act-2 Look Like?
LINKS: LTX Video on Hugging Face: huggingface.co/spaces/Lightricks/ltx-video-distilled LTX STUDIO: https://ltx.studio/ Wan 2.1 VACE: huggingface.co/Wan-AI/Wan2.1-VACE-14B Rubbrband: rubbrband.com Midjourney: midjourney.com Runway: runwayml.comRunways WILD Update & Luma Labs goes BIG!Theoretically Media2025-05-13 | Today I'm diving into the latest exciting updates from Runway ML and Luma Labs that are seriously changing the game in AI imagery and video. Runway ML has dropped some major improvements to their reference feature, and trust me, they absolutely nailed it! We'll see it in action, plus check out some mind-blowing examples from the community. Luma Labs is also stepping up with frame expansion in Dream Machine. Get ready for some cool stuff
Chapters:
00:00 – Intro: Runway ML & Luma Labs Updates 00:27 – Runway ML's Reference Feature Updates 00:56 – Community Showcase: Pulp Fiction Alternate Reality 01:33 – Testing Face Swapping with The Last of Us 01:47 - Results 02:33 – Impressive Details & Quirks 03:28 – Exploring Environments 04:10 – Community Showcase: Abbey Road Composition 05:03 – Experimenting with Wally Wood's 22 Panels 07:03 – Storytelling with Runway References 08:52 – More Community Use Cases 10:04 – Overall Thoughts on Runway Updates 10:34 – Luma Labs Dream Machine Frame Expansion 11:54 – Testing Luma Labs on Different Footage 13:13 – Interesting Quirks in Luma Labs 14:45 – The AI "Knowing" What It Sees 15:01 – Final Thoughts & Outro Resources Mentioned:
LumaLabs Dream Machine: lumalabsai.partnerlinks.io/dd1jzuzx6o87NEW Open Source AI VIdeo, FREE Runway, & Gemini Image Model UPDATES!Theoretically Media2025-05-08 | We've got big news about Tencent's open-source multimodal video model, Hunyuan Custom, and its upcoming Open Source Day! Then, I'll give you a quick refresher on what exactly are multimodal models and how they differ from typical diffusion process AI generation – they're a real game-changer.
We'll then get a little technical (but I'll keep it breezy!) as I walk you through how Hunyuan Custom actually generates video, from reference images and text prompts to the magic behind VAE, LLaVA, and UniDiffuser video. This is where it gets really interesting, as I'll show you how you can use existing video and even audio to drive the AI video generation.
Of course, we need to see the results! I'll show you some examples of Hunyuan Custom's output quality, from human characters and animals to complex scenes with generated backgrounds and actions. And get ready for a shootout! I'm impressed that Hunyuan isn't afraid to go head-to-head with other models like Kling, Pika, and more. We'll look at character referencing, object referencing, and multi-referencing.
The code for Hunyuan Custom should be dropping around May 9th on Hugging Face and GitHub, but I'll share a link where you can try a version of it RIGHT NOW! (Quick note: I had some ISP issues, but you should be good to go!)
Shifting gears, we'll look at Google! While Gemini 2.5 Pro is getting a lot of buzz (interactive visualizers, Godzilla vs. Gorillas simulations!), Gemini 2.0's image model quietly got an upgrade with better visual quality and text rendering. And it's free to use in AI Studio!
Finally, rounding out the freebies, Runway now allows free-tier users to access their image generator, frames, and character reference features. There are limits, but it's a great way to test things out!
CHAPTERS:
00:00 – Intro & What's Coming Up! 00:36 – Tencent's Hunyuan Custom: The Free AI Video Generator! 01:08 – Understanding Multimodal Models 01:32 - The Problem With Diffusion 01:55 - Multimodal Models 02:28 – How Hunyuan Custom Video Generation Works 03:00 - LLava 03:40 – Driving Hunyuan Custom with Video & Audio 04:29 – Hunyuan Custom: The Output Quality! 05:03 - Non Human Inputs 05:27 - Multi Character References 05:47 - Video Inpainting with Reference! 06:18 - Example 2 06:44 - A Day in the Life of A Guy 07:27 – Hunyuan Custom vs. The Competition (State-of-the-Art Shootout!) 07:45 - Example 1 08:18 - Example 2 08:56 - Example 3 09:50 - Example 4 10:49- Example 5 12:08 - Example 6 12:55- Shout out to Hunyaun! 13:11 - Driving Video Inpainting is amazing 13:47 – Try Hunyuan Custom For Yourself! (Code & Links) 14:58 – Google News! 15:55 - Google Gemini 2.0 Image Model Update 16:14 - Using AI Studio 16:37 - Generations 16:56 - What we CAN'T do in Midjourney 17:22 - One Major improvement 18:09 – Runway is Now (Kinda) Free! 19:00 – Wrapping Up!
Don't forget to LIKE this video if you found it helpful, SUBSCRIBE for more AI news and tutorials, and hit that NOTIFICATION BELL so you don't miss out on the latest drops!Runway & Midjourney NEW References: Tips, Tricks, & Showdown!Theoretically Media2025-05-06 | Ever wondered what happens when you pit two AI image generation giants like Midjourney and Runway against each other, especially with their new character and subject referencing updates? Well, you're in the right place. In this video, I'm not just doing an AI deathmatch (though there's a bit of that fun too), but more importantly, I'm diving deep into best practices, tips, and tricks to help YOU get the absolute most out of both platforms. Plus, we'll see what kind of magic or madness ensues when we combine their powers. Let's jump in and explore the cutting edge of AI creativity!
Big Shoutout to LTX Video for sponsoring today's video! Go check out the NEW LTX video model here: https://ltx.studio/?utm_source=social&utm_medium=influencers&utm_campaign=theoreticallymedia_ltxv13b&utm_ad_id=youtube_dedicatedvideo_02042025
What You'll Discover Inside:
A look at Midjourney's OmniReference feature – its strengths, quirks, and how to get the best results (even if it's more "solo reference" for now!).
Tips for using neutral backgrounds and optimal omni strength settings in Midjourney.
How animated, stylized, and synthetic characters shine with Omni Reference.
Tricks to combat blandness and add that "Midjourney spark" using style references.
Exploring lower omni reference rates for cool, stylized character outputs.
A dive into Runway's reference capabilities, including awesome tips from the Runway team and community for creating action sequences and title cards!
Using timestamps in Runway for creative extrapolations.
My experiments combining Midjourney's aesthetic with Runway's strong referencing for some truly unique character creations.
The potential final touch: leveraging face-swapping tools like Face Fusion for enhanced results.
Chapters:
00:00 – Intro: Midjourney & Runway Updates! 00:27 – Midjourney's Omni Reference: First Look 00:56 – Best Practices: Neutral Backgrounds & Omni Strength 01:11 - OmniReference Walkthrough 01:44 - Man in a Blue Business Suit 02:02 - Alt MiaBBS 02:20 – The "Neutral Background" Importance & Unexpected Results 03:06 – Where Omni Reference Shines: Animated & Stylized Characters 03:20 - Viking Girl 1 03:50 – Tip: Using Style References to Combat Blandness 04:16 - Viking Girl in Cyberpunk Land 04:40 – Experimenting with Lower Omni Reference Values 04:55 - Lower Value Experiments 05:14 - Impressive Results 05:35 - Swapping Out Style Ref 06:06 – Over to Runway: Reference Ideas & Tips 06:21 - LTX Video New Model 08:19 – Runway Tips: 3D Models for Action 09:08 - Title Card Generation 09:36 – Creative Uses: Timestamps & Extrapolating in Runway 10:04 – My Runway Experiments: Likeness 10:36 - Inpainting...sorta. 10:53- Overall Runway References Thoughts 11:13 – The Big Question: Can We Combine Midjourney & Runway? 11:28 - Imagine...A Long Time Ago... 11:47 - Over to Runway! 12:21 - And Back to Midjourney! 12:56 – The Final Touch: Face Swapping for Polished Results 13:41- The Final Result(s) 14:12 – Final Thoughts: Tools, Not Versus!
LTX Video: https://ltx.studio/?utm_source=social&utm_medium=influencers&utm_campaign=theoreticallymedia_ltxv13b&utm_ad_id=youtube_dedicatedvideo_02042025BIG Midjourney Updates & New (Free) Lipsync Tool!!Theoretically Media2025-05-01 | Today, I'm diving into some HUGE Midjourney V7 updates that almost feel like a V7.1. Plus, I've got a first look at a seriously impressive new lip sync model you can try right now!We'll also check out a cool new feature from today's sponsor, Recraft – don't worry, it's actually pretty neat!
What's Inside This Video:
Midjourney V7's Big Update: While we're still waiting for the much-anticipated Omni Reference (aka Subject Reference or working Siri!), Midjourney dropped some significant improvements to V7. I'll break down what's new and if it fixes those 'unrealistic poses' and 'blotchy background characters'.
NEW Experimental Aesthetics Command: Meet --exp! I tested this new command that works like 'stylize' to add dynamic elements and creativity. Find out the best values to use (hint: less might be more!). Editor Improvements: Took a quick look at the updated Midjourney editor, focusing on the texture feature which is pretty cool for visual explorations. Got editor tips? Share them below!
V7 Model Polish: Are the Gumby characters and background weirdness gone? We'll see how the updated V7 model stacks up. Omni Reference Sneak Peek: It's delayed, but I got a glimpse of the upcoming Omni Reference feature using CEO David Holtz as the subject! Looks promising and retains that classic Midjourney aesthetic.
Tavis Hummingbird Lip Sync: Checked out the new Hummingbird lip sync model from Tavis. It's available on their site (with a free tier!) and Fall. See how it handles my head bobbles vs. an AI character!
Chapters:
00:00 – Intro: Big Midjourney Updates & New Lip Sync! 00:35 – Tracking V7 Since Launch 01:11 – V7's Initial Quirks 01:30 – The Latest V7 Update (Feels like 7.1?) 01:41 - Where is OmniReference? 02:16 – NEW Command: Experimental Aesthetics (--exp) 02:31 - What is --exp? 02:41- Toast Test! 03:10 – Testing --exp Values (Toast Experiments!) 03:37 - Experimental Toast! 04:04 - Maximum Toast! 04:22 – Finding the Sweet Spot for --exp 04:34 - v7 old prompts now with --exp! 05:32 – Midjourney Editor Updates & Texture Feature 05:57 -Edit and Retexture Tutorial 06:46 – V7 Model Improvements: Less Jank? 07:23- But is it Perfect? No it is not. 07:51 – Omni Reference SNEAK PEEK! 08:43 – Other Reference Options (Runway Recap) 08:55 - Recraft New Feature 09:14 - Recraft Infinite Style Library 11:43 – NEW Lip Sync: Tavis Hummingbird Model 11:54 -Hummingbirds at the White Lotus 12:31 - Where you can use it for FREE! 12:59 – Testing Hummingbird (Me vs. AI Character) 13:16 - Result - AI TIM is here! 13:43 - Where Hummingbird flies! 14:18 – Final Thoughts & Call for Lip Sync Models!
I promised to cover the rolling Midjourney updates, and while Omni Reference keeps us waiting, this V7 refresh and the new --exp command are definitely worth exploring. The Tavis Hummingbird lip sync also looks like a strong contender!What do you think of these updates? And what other lip sync models should I check out for a future shootout? Let me know in the comments below! Don't forget to Like this video if you found it helpful, Subscribe for more AI deep dives, and hit that notification bell!Runways GAME CHANGER for AI Video Is Here!Theoretically Media2025-04-30 | Ever struggled with keeping characters and objects consistent in your AI videos? Well, guess what? Runway just dropped a potential game-changer: the References feature! It might just be the solution we've all been waiting for. In this video, I'm diving deep into Runway's new References tool. We'll explore:
What References does: How it uses Runway Frames to generate a first frame with your character/object reference. Getting Started: Simple steps to use the feature (hint: don't just drag and drop!). Putting it to the Test: See how it handles single characters, multiple characters (like our man in the blue suit and his wolf companion!), and different styles. Tips & Tricks: Learn how to potentially avoid issues like attribute bleed and use styles effectively. Advanced Techniques: Combining references with specific locations, using character sheets, and a sneaky trick for establishing shots. Community Showcase: Check out awesome examples from Dave Clark, Tom Likes Robots, and Andy McNamara. Is it perfect? Not yet. But it's a massive step forward for AI video creation and character consistency. Ready to see if Runway cooked with this one? Let's taxi down the runway and find out! Chapters:
00:00 - Intro: The AI Video Consistency Problem Solved? 00:23 - Runway's Recent Updates (Frames, Gen4) 00:38 - Introducing the References Feature 00:51 - Reference First Release and Congrats to the 48 gang! 01:13 - References Wide Release 01:26 - How References Works (Using Frames) 02:02 - Simple Example: Man in Blue Buinesss Suit 02:37 - How to Use References Correctly 02:56 - One Character Reference 03:32 - Video Output 03:58 - Multiple References: Adding the Wolf 04:12 - Prompting the Wolf 04:37 - Video Output 05:00 - Using Styles with References 05:26- CSI K9 05:39 - Pushing Styles to Break 06:00 - Generating a Crime Movie 06:25- Challenges: Bad Outputs 07:00 - Attribute Bleed? 07:10 - The solve with a new Character 07:33 - Creating Cinematic Scenes (Master & OTS Shots) 07:52- Creating Locations to use as Reference 08:31- Video Output 08:52 - Gen4 vs. Turbo Model Comparison 09:13 - Does Generating in Frames Matter? 09:38 - Video Output 10:12 - Pro Tip: Using Character Sheets & Establishing Shots 11:00 - Sneaky Tip! 11:38 - Video Output 11:41 - Community Examples 12:44 - Final Thoughts: Did Runway Cook?
Let me know in the comments: What do you think of Runway's References feature? Have you tried it yet? What are you excited to create?One Minute AI Video Is HERE & It’s FREE/Open Source!Theoretically Media2025-04-21 | AI Video's ten second generation wall officially SMASHED! I'm diving into something truly game-changing today: FramePack. This open-source tool lets you generate AI videos up to (and even beyond!) ONE MINUTE long, right now, for FREE. Forget those short clips – we're talking serious length here, and it's compatible with generators like Wan, Hunan, and more.
In this video, I'll break down:
How FramePack overcomes the old drifting and coherence issues using cool tech like anti-drifting sampling. How YOU can get it running, whether you have an Nvidia GPU (even with just 6GB VRAM!) using Pinokio, or if you're on a Mac using Hugging Face. Step-by-step guides for both installation methods. Tips for using the tool, including dealing with Tea Caché for better results (or maybe turning it off!). Lots of examples, including successes and some… well, let's call them "learning experiences" (dancing girl goes exorcist, anyone?). Limitations I found, like issues with tracking shots. This tech is brand new and evolving fast, but it's already opening up incredible possibilities for longer-form AI video. Let's explore it together!
Chapters:
00:00 - Intro: Breaking the AI Video Length Barrier! 00:46 - Meet FramePack: The Game Changer? 01:24 - How FramePack Works (No More Drifting!) 02:01 - What questions does Framepack ask? 02:44 - Hardware Requirements (You Might Already Have It!) 03:08 - Method 1: Installing with Pinocchio (Nvidia Users) 04:18 - Method 2: Using Hugging Face (Mac & Others) 05:49 - Using Frame Pack: Settings & Tips (TeaCaché Explained) 07:27 - Generation Examples & Experiments (Hourglass Timer!) 08:36 - More Examples: Detective 08:56 - Dancing Girls 09:42 - TeaCaché On vs. Off Comparison 10:10 - Known Limitations (Tracking Shots) 10:45 - Some great use cases (Moving Pictures) 11:20 - Endless Lofi Girl 11:54 - This is not the only one: The TTT Model Resources Mentioned:
Pinokio Installer: https://pinokio.computer/ Hugging Face Space (Duplicate This!): huggingface.co/spaces FramePack Paper: github.com/lllyasviel/FramePack TTT (Tom & Jerry) Paper: test-time-training.github.io/video-ditVeo-2 Drops on LTX Studio (Massive Price break!)Theoretically Media2025-04-21 | he Veo-2 PRICE BREAK we’ve been waiting for! LTX Studio have dropped Veo-2 on their platform with a INSANE launch promo & extra Veo credits! You’ll want to check this out! https://ltx.studio/lp/veo-2-offerThe AI Video Tool for WILD Camera Shots! Higgsfield Deep Dive & Review!Theoretically Media2025-04-17 | Some WILD AI Camera Here! Start your 7-day free trial with HoneyBook and see the difference - bit.ly/HoneyBook-Theoretically_media
Today I'm diving deep into HiggsField, an AI video platform that's making waves with some seriously wild virtual camera movements! Ever seen those cool, hyper-stylized AI videos popping up on your feed? Chances are, they came from HiggsField.
I spent some time exploring whether this platform is just a gimmick or a genuinely useful tool for creators. Is it all just cherry-picking, or can it really deliver? Let's find out! LINKS: HiggsField: higgsfield.ai escape Platform: escape.ai Paige Piskin : https://x.com/PaigePiskin/status/1912313290409062697
My thanks to today's sponsor: HoneyBook is more than just a CRM platform. It's more of a behind-the-scenes partner to eliminate busywork, reclaim your time, and keep you focused on what truly matters. bit.ly/HoneyBook-Theoretically_media
In this video, I'll walk you through:
What is HiggsField? A look at the platform and its niche in hyper-stylized shots. Exploring the Presets: From explosions and bullet time to the... unique... tentacle effect. (Spoiler: I get a little Lovecraftian later! ) Testing the Camera Movements: Putting presets like Zoom Out, Kiss POV (yes, really!), 360 spins, Snorri Cam, Disintegration, and Glass Shatter to the test. Bullet Time Deep Dive: My personal favorite effect! We even recreate a Matrix scene (with a surprise Dwight Schrute lookalike!). Mixing & Matching Effects: Combining presets like Building Explosion and Arc for dynamic shots. Overcoming Limitations: Tackling the 5-second clip limit with the last-frame-first-frame trick and discussing potential extension solutions. Style Consistency: Does it maintain styles like anime, or does it lean towards realism? 9:16 Format: Why Higgs Field shines for TikTok and Instagram content. Is it Worth It? My thoughts on using Higgs Field for cinematic projects vs. social media, plus a breakdown of the pricing.
Chapters:
00:00 - Intro: Wild Camera Moves! 00:44 - Exploring Higgs Field Presets 01:34 - Useful vs. Gimmicky Effects 02:00 - Testing: Noir Detective Zoom Out 02:35 - Zoom and Arc 03:15 - Michael Bay Level Explosions! 03:54 - The Virtual Smooch: Kiss Preset 04:46 - 360 Spins 05:05 - Snorri Cam Showcase 05:58 - Disintegration 06:22: Tentacles (Lovecraft Time!) 07:08 - HoneyBook 08:52 - Bullet Time Fun (Matrix BTS!) 09:48 - Side Note: John Gaeta & escape.io 10:24 - Cool Effect: Glass Shatter 10:49 - Mixing Presets: Explosions + Arc 11:41 - Extending Clips: The 5-Second Limit 12:19 - Last First Frame 13:15 - Style Consistency 13:51- 9:16, where this flies 14:10 - But still good at 16:9 14:35 - Pricing & Final Thoughts
HiggsField offers some genuinely impressive (and sometimes hilarious) tools for creating eye-catching AI video content, especially for shorter formats. While the 5-second limit is a hurdle, the unique camera movements and effects make it a platform worth exploring, even if just for adding some 'zazz' to your projects.
What do you think? Is Higgs Field a useful tool or just a fun gimmick? Let me know in the comments below! 👇
Don't forget to LIKE 👍 if you found this helpful and SUBSCRIBE for more AI video explorations!Kling 2.0 is HERE! Is it STILL the BEST AI Video Generator?!Theoretically Media2025-04-15 | Kling 2.0 just dropped, and you know I had to dive right in to see if the reigning champ of AI video generation got even better. In this video, I'm putting Kling 2.0 through its paces, comparing it to the previous 1.6 model (which was already crushing it!) and seeing how it stacks up against the competition like Google's VEO 2. We'll look at text-to-video, image-to-video, new features, and find out what's still missing and what's coming next. Let's see if Kling keeps the crown! 👑
Chapters:
00:00 - Intro: Kling 2.0 Arrives! 00:41 - First Look: Fidelity & Coherence Boost 01:03 - Text-to-Video: Game of Thrones Direwolves (and Real Life!) 01:26 - Direwolf Results 01:59 - Text To Video Test 2 02:13 - Image-to-Video Quick Test (vs. VEO 2 Style) 02:59 - Overall Text To Video Impressions 03:15 - Text-to-Video: Strengths & Weaknesses (Cowboy Cosplay?!) 03:43 - Coherent Fast Motion: Kung Fu Fight Scenes! 04:41 - More Examples (Thanks Justin!): Punching Bags & Blizzards 05:19 - Running Test 05:50 - Generation Specs & Camera Control 06:09 - Lens and Camera Motion Callouts 07:14 - Image-to-Video Deep Dive (ft. Kolors 2.0) 07:50 - Sci-Fi Vibe Short 08:32 - Saucing Up the Footage 09:02 - Less Generations 09:22 - Impressive Walking Cycles 09:58 - Stylistic Retention with Image to Video 10:49 - AI Girlfriends and Crusty Pirates 11:45 - Final Frame Trick 12:26 - NEW Multi-Elements Feature 13:55 - Final Verdict: Still the King?
What I Cover:
Comparing Kling 2.0 vs 1.6 and Google VEO 2. Testing Text-to-Video: Examples range from direwolves and stock footage to kung fu and slightly awkward cowboys. Exploring Image-to-Video: Checking consistency, character animation, style adherence, and complex motion like walking and fighting. Camera Control & Lens Simulation: Does asking for an "85mm lens" work? New Multi-Elements Feature: A quick look at swapping elements between videos (using the 1.6 model for now!). Creating a short sci-fi piece using Kling 2.0, Udio for music, and Topaz for upscaling.
What do YOU think of Kling 2.0? Is it still the best AI video generator out there, or are you using something else? Let me know down in the comments! 👇
Don't forget to LIKE 👍 if you found this helpful and SUBSCRIBE for more AI explorations!
Thanks for watching! Tim!Massive Veo-2 News From Google & $300 of FREE Use?!Theoretically Media2025-04-09 | Google's Cloud Next event just wrapped, and wow, did they unload a ton of AI news! It felt a bit like a shotgun blast of announcements, but I'm honing in on the cool creative AI stuff – the latest on Veo 2, Imagen 3, and a brand new AI music generator called Lyra. Did Google cook? Yeah, they did! But can you get a plate easily? Well... maybe it's more like the drive-thru for now.
In this video, I break down the biggest creative AI takeaways from Google Cloud Next:
What's New: We got updates on the already impressive Veo 2 text-to-video, the next iteration of their image generator (Imagen 3), Chirp 3 for text-to-speech, and the new Lyra AI music tool. Google's flexing that they're the only platform doing video, music, image, and speech natively... sort of. Veo 2 Power-Ups: I dive into the new Veo 2 features like inpainting (think magic eraser for video!), aspect ratio changes, camera controls, and extending video length. Plus, a cool look at how Veo 2 helped bring The Wizard of Oz to the Sphere! Imagen 3 & Chirp 3: Imagen 3 gets better detail and even image editing capabilities now. Chirp 3 lets you create custom voices with just seconds of audio. Lyra Music: Google's answer to AI music? It generates short, instrumental jingles – maybe not dropping fire beats just yet, but useful for content creators. Vertex AI Access: Here's the catch – most of this cool stuff lives on Google's Vertex AI platform, which looks enterprise-y but is actually accessible. FREE AI Fun?: The best part? I show you how you might be able to test drive Imagen 3 and the powerful base Veo 2 on Vertex AI for FREE right now using their trial credits (seriously, my cost is $0 so far!). No guarantees on how long this 'open cookie jar' lasts, though! Gemini 1.5 Pro: Also, Gemini 1.5 Pro is widely available and has honestly become my daily driver LLM. I even show a neat trick using it with Veo 2.
00:00 - Intro: Google Cloud Next AI Overload! 01:06 - Veo 2 & The Wizard of Oz Sphere Project 02:13 - Gemini 1.5 Pro Goes Wide 02:32 - Creative AI Suite: Veo 2, Imagen 3, Chirp 3, Lyra 03:19 - Lyra AI Music Generator: First Look 04:17 - Imagen 3 Gets Updates & Editing 04:38 - Chirp 3: Custom Text-to-Speech 04:50 - Veo 2 NEW Features: Inpainting, Camera Controls & More! 05:30 - Inpainting in Veo-2 05:52 - Expanding the Frame in Veo-2 06:21 - Camera Controls in Veo-2 06:40 - First Frame Last Frame 06:57 - Extend Video in Veo-2 07:27 - Editing Toolbar in Veo-2 07:43 - Accessing Google's AI: The Vertex Platform 08:48 - How to Use Vertex AI (FREE Veo 2/Imagen 3?!) 10:43 - Cool Trick: Gemini + Veo 2 Prompts 12:01 - Final Thoughts: Grab the Free AI While You Can! What do you think about these Google AI updates? Are you going to try accessing Veo 2 or Imagen 3 on Vertex AI? Let me know in the comments below!
Don't forget to LIKE this video if you found it helpful and SUBSCRIBE for more AI adventures!AI QUAKE Is Here & You Can Play It! Is it a GameChanger?Theoretically Media2025-04-07 | Microsoft just dropped an AI bomb on an Id Software classic! They've unleashed an AI-powered version of the legendary Quake II, and YES, you can play it RIGHT NOW! But should you? 🤔 Let's dive into this wild experiment, ask the big "why," and try to figure out where this whole AI gaming thing is headed. Grab your Railgun and some Quad Damage – it's gonna be a trip!
What's Going On with AI Quake II?!
This isn't your daddy's Quake (unless your dad is super into cutting-edge AI!). Microsoft Research, the wizards behind the curtain, have unleashed "Muse," their AI world agent, to recreate Quake II. Following in the footsteps of Google's AI Doom, this project is seriously mind-bending. But hold on a sec... is it actually Quake II? Let's break it down!
Chapters:
00:00 – The AI Quake II Drop! - Microsoft's surprise release and initial thoughts. 00:23 – What Exactly IS AI Quake II? - Diving into the tech and its predecessors like Google's AI Doom. 00:45 – A Quick Quake II History Lesson - A blast from the past on the original game's impact. 01:15 – From Xbox to AI: The Evolution - Tracing Quake II's journey to this AI iteration. 01:56 – Meet Muse: The AI Behind the Magic - Exploring Microsoft's AI world agent and its upgrades. 02:21 – Tech Specs & What This Isn't - Clearing up confusion: it's research, not a polished game! 02:52 – AI-Generated Worlds: The Core Concept - Understanding how this interactive AI video works. 03:10 – Muse's Level Up: Faster and Bigger! - Examining the improvements in frame rate and resolution. 03:42 – Training Time: From Years to a Week?! - The surprisingly short training period for this AI model. 04:12 – The Big Question: Is It a Good Game? - Spoiler alert: not quite yet! 04:21 – The Janky Reality: Object Permanence & More - Facing the current limitations of AI game generation. 04:56 – Hands-On (Kind Of): My Hilarious Gameplay Experience - Trying out the keyboard-only controls and weird glitches! 06:05 – Game Over (Literally): The Short Play Session - Highlighting the limited playtime. 06:15 – Why Does This Exist?! The Big Picture - Exploring Microsoft's vision for AI and game preservation. 07:00 – The Future of AI in Gaming: My Thoughts - Reflecting on the progress and what's to come. 07:56 – The "Can It Run Crisis?" of AI Games! - My proposal for a new AI benchmark.
This AI Quake II is a research project by Microsoft's "Muse" (formerly WHAM!). It generates interactive video at roughly 10 frames per second (up from 1!). The output resolution is 640x360 (doubled from the previous model). The Quake II model was trained on about one week of Quake II video. Controls are currently limited to keyboard input (WASD for movement, arrow keys to look, F to fire). Object permanence is a major challenge – if you look away for less than a second, things disappear! Health values and other in-game counters aren't super reliable. Gameplay sessions are currently limited in duration. Why Bother with AI Quake II?
While it's not exactly replacing your gaming rig anytime soon, this project hints at a fascinating future. Phil Spencer from Microsoft Gaming has talked about using AI to learn old games and make them playable on any platform, regardless of the original hardware. Think game preservation on a whole new level!
The Future is Now (Kind Of):
We're seeing rapid advancements in generative AI for games, from AI-powered NPCs to 3D asset creation. While a fully AI-generated AAA title is still a ways off, projects like Muse and Google's Genie are laying the groundwork. Could this be the beginning of the "ChatGPT moment" for video games? I think we might just be seeing the very first sparksMidjourney V7 Is Here! Was It Worth The Wait?Theoretically Media2025-04-04 | Midjourney V7 is finally here, and I'm diving deep! I'm testing out the new features, including the personalization profile and the super-fast draft mode. Is it worth the hype? Let's find out!
In this video, I'll cover:
My first impressions of Midjourney V7. The new personalization profile setup. A look at the draft mode and its speed. Prompt tests and image quality comparisons. What's missing and what's coming next. If you're into AI art, you won't want to miss this! Hit like, subscribe, and share your V7 thoughts below!
Chapters:
00:00 – Intro: Midjourney V7 Arrival! 00:24 – Just How Long Has It Been? 00:55 - The Landscape Has Changed 01:32 – Key Features Overview 01:45 - Getting Started With Personalize 02:35 - Options Toolbar Changes 03:10 – Prompt Testing Toast 03:46 - Prompt Test Beauty 04:11 - Prompt Testing Surreal 05:03- Prompt Testing Wizards 06:09 - Hard Prompt Test 06:44 - New Feature: Draft Mode 07:32 - Draft Mode Test 07:55- Missing Features 08:13 - More Hard Prompts 08:45 - Blurry Faces 09:04 - Impressions 09:36 - What is Coming Up for Midjourney? 10:04 - Midjourney Video 10:42 - Is Midjourney the Best Image Generator Around? 10:53 – Does "the best" matter? 11:08 - Coming up NextAI Video Acting Levels Up!Theoretically Media2025-04-03 | Bytedance have unveiledDreamActor-M1, a new AI video model that brings full-body, expressive human animation to a whole new level! #aivideo #aitoolsRunway COOKED for GEN-4! Ultimate Deep Dive & Review!Theoretically Media2025-04-01 | Today, we're diving deep into RunwayML's Gen 4, the latest update to their AI video generation model. Runway claims that Gen 4 boasts improved fidelity and output quality. More importantly, Gen 4 introduces better consistency in character, location, and color grading.
While the highly anticipated reference feature isn't available at launch, there's still plenty to explore. I'm putting Gen 4 through its paces with a series of tests, checking out community outputs, and sharing some best practices.
We'll take a look at everything from image to video generation, character consistency, and even some fun experiments with text and effects
I’ll also be comparing Gen 4 to previous Runway versions like Gen 3 and Gen 2.
Runway's Gen 4 is a significant step forward, and I'm excited to share my findings with you. There are still more updates on the way. So, buckle up, and let's jump into the world of Gen 4!
00:00 - Intro to Runway Gen 4 00:29 - Gen 4 Overview and Key Features 01:17 - Gen 4 at Launch 01:48 - Frames to Video (Man In the Blue Suit) 01:59 - First Video Test 02:24 - Frames Image Generation 02:44 - London Test 02:58 - Gen 4 vs. Gen 3 vs. Gen 2 04:02 - Gen-4 Text (Woman in the Red Dress) 05:13 - Impressive Wide Angle Shot 05:48 - Gen 4 Wonk 06:29 - Expand Feature With Gen-4 07:00 - Fight Sequences (Raging Bull) 07:32- Noir Test & What Reference Might REALLY Be 08:15 - Noir Test 2 08:42 - How Powerful Will Reference Be? 09:55 - Image to Video 10:29 - No Prompt with Image To Video Test 11:07 - Working with Multiple Faces 12:13 - Grandma with a Flamethrower 12:21 Style Consistency with Image to Video 12:52 - Cyberpunk Woman 13:55 - Gen-4 To Restylize 13:59 - Community Outputs Showcase 15:58 - Final Thoughts on Gen 4This AI Image/Video Platform Opens Up So Many Possibilities (And You Can Try It For Free!)Theoretically Media2025-03-31 | Let's take a tour of one of the most interesting AI generation platforms I've come across: Flora. If you're into AI art, image editing with Gemini, and even video generation, this platform has it all.
I know the workflow might look a bit intimidating at first – all those Blocks and connections! But trust me, it's not as scary as it seems. I'll walk you through the basics, from generating images with text prompts to using cool features like style reference and video-to-video generation.
We'll be playing around with Gemini's editing features, creating our own character references, and even training a custom style. Plus, I’ll show you how to take those images and turn them into videos!
Whether you're into clean, organized workflows or a bit of creative chaos, Flora has something for you. And the possibilities? Let’s just say they got me thinking about fight sequences and character turnarounds!
Check out Flora for yourself! They offer 2000 free monthly credits so you can explore the platform and see if it’s a good fit for you.
CHAPTERS 00:00 - Intro to Flora: An AI Playground 00:28 - The AI Murderboard Isn't Scary 00:52 - Understanding the Workflow 01:19 - Text to Image Generation with LLMs 01:55 - Image Generation Options 02:42 - Video Generation Options 03:21 - Organization on a Canvas 03:53 - Gemini's Image Editing Features 04:46 - Flora Styles 05:25- Cinematic Crime Film Style 06:30 - Training Your Own Style 07:33 - Testing Out a Custom Style 08:27 - Video Generation Tests 08:57 - Off Book Video to Video Generation 09:50 - Character Edits With Gemini 11:26 - Impressive Turnarounds! 12:37 - Thoughts on Turnarounds Use Cases 12:57 - Advanced Flora Technique 13:25 - Storyboarding with AI 13:54- Flora's Free and Paid Plans 14:12 - Next Up for FloraBehind The Scenes Of An AI Film (Masterclass & Cost Breakdown!)Theoretically Media2025-03-27 | Hey everyone! I'm super excited to finally share a full production breakdown of my AI short film, "The Bridge." The response has been incredible (almost 400,000 views across platforms!) and I'm here to spill all the secrets on how I made it. In this video, I’ll walk you through the entire process, from pre-production and AI tools, all the way to final post-production. I’ll also dive into the costs and compare them to traditional filmmaking.
If you haven’t seen the short yet, don’t worry, I’ve included it in the video!
My Thanks to Recraft for Sponsoring Today's Video! Check out Recraft – go.recraft.ai/media. Use my code MEDIA for $12 off any paid plan.
CHAPTERS 00:00 – Introduction 00:37 - The Bridge Views 01:20 - The Bridge 03:37 – Pre-Production 04:11 – AI Tool Selection 05:10 - Re-Inspired 05:31 – Prompt Engineering 06:13- Working with an LLM on a Film 06:33 – Veo-2's Super Power 07:50 – Achieving Visual Consistency 09:10 – Audio Production 09:52 – Lip Syncing with Hedra 10:32 - Upscaling 11:16 – More Upscaling 11:52 - Making a Poster w/ Recraft 13:23 – Post-Production in Premiere Pro 13:55 - Death's Voice 14:40 – Is it Perfect? 15:25 - Cost Breakdown 17:01 - Comparison To Traditional Filmmaking 18:11 – Make Movies 18:55 - It's just not there yetOpenAIs Stunning Image Model Has Some Cool Tricks!Theoretically Media2025-03-26 | OpenAI has dropped a brand NEW AI Image generation model, and it's NOT Dall-E 4! In this video, I'm taking you on a deep dive into this remarkable AI Model and showing you EVERYTHING it can do. We'll explore its impressive capabilities, uncover some hidden features, and yes, even talk about its quirks. Is this the end for avocado chairs?!
In this video, I cover:
* OpenAI's new AI image generator (it's not Dall-E!) * Image generation AI tools and comparisons * AI art techniques and workflows * Text-to-image AI generation * AI character design and consistency * Sora AI video generation updates * AI art community highlights * New AI tools and software
This new AI is seriously impressive, but it also has some limitations. I'll show you what I've discovered in my testing, including how it handles text, image referencing, and creating consistent characters. Plus, we'll take a look at the latest Sora updates and some incredible AI art from the community.
If you're interested in AI art, image generation, or just the latest in AI tech, you NEED to watch this!
Chapters: 00:00 - Intro: OpenAI's New Image Generator - Is Dall-E Dead? 00:18 - Quick Announcement: My AI Short Film - The Bridge 00:41 - Goodbye Dall-E? First Look at the NEW AI Model 01:28 - Image Generation Tests: Blue Suit Guy, Samurai & More! 02:11- Controls and Options 03:04 - Samurai Test 03:15 - Clown with a chainsaw 03:45 - AI Challenge: Complex Prompts with the Woman in the Red Dress 04:17 - Remixing for Different Angles 04:49 - Creative AI: Underwater Scenes, 90s Nostalgia & VHS Tapes 05:24 - The VHS Tape 05:48 - Text Generation is INSANE! Alan Wake Novelization Test 06:56 - GTA 7 Box Art Test 07:52 - Image Referencing EXPLAINED: How to Use Reference Images 08:04 - Scrambling Faces 08:26 - Not John Wick 09:04 - Multiple Image References 10:24 - Illustrated to Photo with Image Reference 11:13 - Sora Time 11:48 - Community Outputs 13:04 - More AI Tools You NEED to Know: Reve, Ideogram 3.0THE BRIDGE: A Stunning AI Film Created with Veo-2.Theoretically Media2025-03-24 | Presenting: The Bridge. An AI Short film utilizing Google’s Veo-2. I’m really proud of this one, as my goal (as always) is to push storytelling, performance, and narrative in this emerging art form, and I feel like I managed to pull something close that off here.
Every shot here utilized Veo-2, although there were a few post-generation tricks here and there.
I’ll cover everything in detail in an upcoming video. In the meantime, I hope you enjoy the short.