Uploaded September 2026 | Updated November 2026, 1 day ago
Dreamina just rolled out the Seedance features a lot of us have been waiting on. The canvas got a proper overhaul, with an AI agent that will actually plan and organize a shoot for you (with some caveats I'll show you), there's finally an Elements library so your characters — voice included — follow you into any prompt, there's a new set of Skills on the generate side, and, surprisingly, MiniMax H3, GPT Image 2 and Nano Banana Pro are all sitting inside the canvas now.
And then the one I think everyone's actually going to use: Seedance 2.5 Preview. Draft a shot at 480p for significantly less, dial in the prompt, then hit generate in full quality and Seedance re-renders that exact same shot at 1080. Not an upscale — a real re-render, same output. It's in preview right now; hopefully it's live for everyone within a week or so.
SPONSOR
This video is sponsored by Genspark — big thanks to the team for backing this one.
► Try Genspark Design: genspark.ai/agents?type=design&utm_campaign=TheoreticallyMedia04&utm_source=yt
One prompt, any design, and it comes back fully editable — posters, launch kits, thumbnails, video teasers, even a web page for your film. Templates are free, and you get free compute credits every day you log in.
WHAT'S IN THIS ONE
- The revamped Dreamina canvas and its much-improved AI agent — plus where I'd still take manual control (the actual shot prompt).
- Three tests: a PI-office dialogue scene recast with Tuesday Sinclair and James from Death Walks Into a Bar; the flamethrower-girl stress test from the Seedance 2.0 days; and the same test again, this time feeding the agent the original storyboards as inspiration.
- The agent that built transparent PNGs of every element on its own, wrote its own brief and asset list, and then named my flamethrower girl Lyra. (That's the barbarian from The Bridge. Nothing conspiratorial — but interesting.)
- The new edit-segment feature — and the snootiest possible fix for glowing eyes.
- Elements: put a character in once, give her a custom voice, then just @ her in any prompt.
- MiniMax H3, GPT Image 2, Nano Banana Pro and Seed Audio 1.0 all available inside the canvas.
- PJ Ace's Skyline Heist board — character sheets, a note to the animator, and an acting system worth stealing.
- Skills on the generate side: iconic film style, cinematic long takes (past 30 seconds), film storyboard, and micro-expression prompts.
- Seedance 2.5 Preview: 480p drafts, then a full-quality re-render of the same shot.
- What's coming: BytePlus Dramagic (script analysis, storyboarding and video review — enterprise-side, in beta) and the reports that ByteDance is close to releasing its own world model.
LINKS MENTIONED
Dreamina:
dreamina.capcut.com/ai-tool/home?utm_source=Officiaaccount&utm_campaign=sd25&utm_content=25ytb
PJ Ace — Skyline Heist (Nexus): youtu.be/vvIenAHD41A?si=v6K6oODd5jp3fium
Dramagic Beta Signup: byteplus.com/en/contact-us/dramagic-x
Chapters:
00:00 Not Seedance 3.0 — but a big Dreamina update
00:24 The revamped canvas
00:57 The much-improved AI assistant
01:26 GPT Image 2, Nano Banana Pro, Seed Audio 1.0 & MiniMax H3 in the canvas
02:00 Test 1: recasting a scene with Tuesday Sinclair & James
03:00 Test 2: the flamethrower-girl stress test
03:53 Wait, why did it name her Lyra?
04:17 The agent's first three shots (and the jump cuts)
05:25 Test 3: feeding it the original storyboards
06:18 The result, and my notes
07:11 Edit segment: prompting out the glowing eyes
07:45 Verdict: let the agent organize, prompt the shot yourself
08:44 Elements: characters (and voices) you can @ in any prompt
09:21 PJ Ace's Skyline Heist board
10:07 What to steal from PJ's board
11:44 Sponsor: Genspark Design
15:45 Skills on the generate side
16:50 Seedance 2.5 Preview: cheap 480p drafts
17:59 Full quality: the same shot re-rendered at 1080
18:57 Coming up: BytePlus Dramagic and a ByteDance world model?
Theoretically News — the weekly newsletter: theoreticallymedia.com/newsletter
CHAPTERS
Dreamina just rolled out the Seedance features a lot of us have been waiting on. The canvas got a proper overhaul, with an AI agent that will actually plan and organize a shoot for you (with some caveats I'll show you), there's finally an Elements library so your characters — voice included — follow you into any prompt, there's a new set of Skills on the generate side, and, surprisingly, MiniMax H3, GPT Image 2 and Nano Banana Pro are all sitting inside the canvas now.
And then the one I think everyone's actually going to use: Seedance 2.5 Preview. Draft a shot at 480p for significantly less, dial in the prompt, then hit generate in full quality and Seedance re-renders that exact same shot at 1080. Not an upscale — a real re-render, same output. It's in preview right now; hopefully it's live for everyone within a week or so.
SPONSOR
This video is sponsored by Genspark — big thanks to the team for backing this one.
► Try Genspark Design: genspark.ai/agents?type=design&utm_campaign=TheoreticallyMedia04&utm_source=yt
One prompt, any design, and it comes back fully editable — posters, launch kits, thumbnails, video teasers, even a web page for your film. Templates are free, and you get free compute credits every day you log in.
WHAT'S IN THIS ONE
- The revamped Dreamina canvas and its much-improved AI agent — plus where I'd still take manual control (the actual shot prompt).
- Three tests: a PI-office dialogue scene recast with Tuesday Sinclair and James from Death Walks Into a Bar; the flamethrower-girl stress test from the Seedance 2.0 days; and the same test again, this time feeding the agent the original storyboards as inspiration.
- The agent that built transparent PNGs of every element on its own, wrote its own brief and asset list, and then named my flamethrower girl Lyra. (That's the barbarian from The Bridge. Nothing conspiratorial — but interesting.)
- The new edit-segment feature — and the snootiest possible fix for glowing eyes.
- Elements: put a character in once, give her a custom voice, then just @ her in any prompt.
- MiniMax H3, GPT Image 2, Nano Banana Pro and Seed Audio 1.0 all available inside the canvas.
- PJ Ace's Skyline Heist board — character sheets, a note to the animator, and an acting system worth stealing.
- Skills on the generate side: iconic film style, cinematic long takes (past 30 seconds), film storyboard, and micro-expression prompts.
- Seedance 2.5 Preview: 480p drafts, then a full-quality re-render of the same shot.
- What's coming: BytePlus Dramagic (script analysis, storyboarding and video review — enterprise-side, in beta) and the reports that ByteDance is close to releasing its own world model.
LINKS MENTIONED
Dreamina:
dreamina.capcut.com/ai-tool/home?utm_source=Officiaaccount&utm_campaign=sd25&utm_content=25ytb
PJ Ace — Skyline Heist (Nexus): youtu.be/vvIenAHD41A?si=v6K6oODd5jp3fium
Dramagic Beta Signup: byteplus.com/en/contact-us/dramagic-x
Chapters:
00:00 Not Seedance 3.0 — but a big Dreamina update
00:24 The revamped canvas
00:57 The much-improved AI assistant
01:26 GPT Image 2, Nano Banana Pro, Seed Audio 1.0 & MiniMax H3 in the canvas
02:00 Test 1: recasting a scene with Tuesday Sinclair & James
03:00 Test 2: the flamethrower-girl stress test
03:53 Wait, why did it name her Lyra?
04:17 The agent's first three shots (and the jump cuts)
05:25 Test 3: feeding it the original storyboards
06:18 The result, and my notes
07:11 Edit segment: prompting out the glowing eyes
07:45 Verdict: let the agent organize, prompt the shot yourself
08:44 Elements: characters (and voices) you can @ in any prompt
09:21 PJ Ace's Skyline Heist board
10:07 What to steal from PJ's board
11:44 Sponsor: Genspark Design
15:45 Skills on the generate side
16:50 Seedance 2.5 Preview: cheap 480p drafts
17:59 Full quality: the same shot re-rendered at 1080
18:57 Coming up: BytePlus Dramagic and a ByteDance world model?
Theoretically News — the weekly newsletter: theoreticallymedia.com/newsletter
CHAPTERS





![AI Video Just Stepped Into the Real World!
Your AI characters can now stand in your actual room, and react to whats in it!
Simulon is back: turn a character image into a 3D neural asset, place it in the real world through your phones camera, act out the scene with your own camera move, and the app regenerates the take with the character responding to what you do and say.
Also: a kitbash into Kling 4.0 and Genie 4, and Alibabas Apsara slide with Wan, Happy Horse and Happy Shrimp on the board.
WHATS IN THIS ONE
- Simulon, back from 2023 (2.0 shipped October 9, Reality-Aware Rendering October 28): upload a character reference, it builds a 3D neural asset, you place, scale and rotate it in your real space through the phone camera, then generate. Not real time yet: you prompt the action, or shoot your take first and let it render.
- Flamethrower Girl, life-size at my bar: my camera move, my location, no world-model hallucination (the ball on the floor is really there). Mini version on the desk, then a jungle-attire run across the bar.
- Kitbash 1: the Simulon output into Kling 4.0 video-to-video, location swapped.
- Two characters at once: Renfield and Flamethrower Girl play tennis at the park (wonky, but consistent in the space). Then Flamethrower Girl walks Simulons library tiger through my living room, and the two interact without being asked.
- Isnt this just reference-to-video? Mostly, yes (the back end feels Minimax-ish to me, a guess). The difference is blocking your characters on set, run-and-gun.
- Reality-Aware Rendering: the characters respond to what you do and say in the take. I poke the tiger and mini Flamethrower Girl with my finger. A mech goes aggro at Astro the cat, who could not care less.
- Renfield tends bar and reacts to my voice. The rum keeps disappearing.
- Roadmap: Simulon tells me voices and assignable personalities are coming. Their own demo shows a character taking spoken direction.
- Kitbash 2: a Simulon output into Genie 4, then a walk through the back rooms of my own house.
- Pricing: free to try on iPhone (100 starter credits, library characters only). Plus is $14.99 a month (your own characters from images or words, commercial use for individuals); Pro is $39.99 (3x the usage, business use). Android is next; Simulon tells me its waiting on Google.
- Alibabas Apsara slide: Wan, Happy Horse and Happy Shrimp on the model-family board. [Tim — November isnt on the slide; keep it only with a source, linked below.]
SPONSOR
This video is sponsored by Artlist. 3D Model is now its own category on Artlist, next to where you already generate images, video, voiceover and music: a text prompt or a photo goes in, a production-ready 3D asset comes out in about a minute, with Hunyuan 3D, Tripo H3.1 and Meshy v7 in the lineup. Once its a real 3D object theres no wrong angle anymore, and the video model finally has a reference that doesnt drift.
► Try the new 3D models over on Artlist, who were kind enough to sponsor todays video: https://artlist.io/artlist-70446/?artlist_aid=TheoreticallyMedia_4024&utm_source=affiliate_p&utm_medium=TheoreticallyMedia_4024&utm_campaign=TheoreticallyMedia_4024
LINKS
Simulon on the App Store: https://apps.apple.com/us/app/simulon/id6670765943
Simulon: https://simulon.com/
Reality-Aware Rendering, announced by Divesh Naidoo: https://x.com/diveshnaidoo/status/2115477721455214623
Simulons caveman short film: https://x.com/Simulon/status/2115519228564693170
What was actually filmed: https://x.com/diveshnaidoo/status/2115540443580481759
Genie 4 hands-on: https://www.youtube.com/watch?v=kJgYSiIZMb8
Kling 4 video: https://www.youtube.com/watch?v=U9tFP81PSbQ
Dead Sea (Renfields film): https://www.youtube.com/watch?v=o_90Vd8rAwI
Alibabas Apsara slide: [Tim — the post you took the slide from]
Newsletter: https://theoreticallymedia.com/newsletter/
CHAPTERS
00:00 Can your AI characters live in the real world?
00:14 Simulon is back
00:48 Mini Flamethrower Girl on my desk
01:09 How it works: phone camera, character ref to 3D, place it
01:47 Life-size Flamethrower Girl at the bar
02:33 Your camera move, your location
03:08 Kitbash: Simulon to Kling 4.0 video-to-video
03:30 Two characters: Renfield and Flamethrower Girl play tennis
04:20 From Dead Sea to the tennis court
04:38 Flamethrower Girl, tiger trainer
05:21 Artlist 3D (sponsor)
07:36 Isnt this just reference-to-video?
08:19 Reality-Aware Rendering: poke the tiger
09:07 Mech vs. Astro the cat
10:00 Renfield tends bar (he hears my voice)
10:50 Roadmap: voices, personalities, spoken direction
11:58 Simulons caveman short film
12:11 Kitbash: Simulon to Genie 4
13:19 Pricing and availability (free on iPhone, Android next)
13:49 Wan and Happy Horse: Alibabas Apsara slide
14:08 Wrap
#AIVideo #AINews #Simulon #AR #FlamethrowerGirl #Genie4 #Kling4 #Artlist AI Video Just Stepped Into the Real World!](https://i.ytimg.com/vi/mpqgn9DMld4/mqdefault.jpg)




