Uploaded January 2026 | Updated November 2026, 5 days ago
Runway Gen 4.5 Image-to-Video is finally here, and it is a massive leap forward for AI filmmaking. In today’s video, we aren't just looking at the new model—we are stress-testing it. From character consistency and complex camera movements to how well it handles "novel" elements (like unexpected bears), we see exactly what Gen 4.5 is capable of.
We also take a stroll down memory lane to compare Gen 4.5 against Gen 3 and even the original Gen 1 to see just how far this technology has come. Plus, I catch you up on the massive UI updates, Story Panels, and how to use the powerful new Node-Based Workflows.
⚡ If you're NEW: Get 20% OFF RunwayML with this link: runwayml.com/?utm_source=creator&utm_medium=sponsored&utm_campaign=gen45&utm_content=theoretically-media
📩 Join my AI Newsletter for weekly tips & workflows: theoreticallymedia.beehiiv.com
IN THIS VIDEO: We explore the limits of the new Image-to-Video model, test the "Gritty Film" aesthetic in text-to-video, and fix the "paralysis" issues seen in previous generations. I also break down the new "Workflows" tab and show you how to properly use the Story Panel Upscaler to get high-res narrative shots.
CHAPTERS
00:00 Intro: Gen 4.5 Image-to-Video Release
00:28 Early Access
00:44 A Look Back
01:03 Revisiting Gen 2 Tests
01:16 Reviewing Gen 2 Output
01:44 Reviewing Gen 3 Output
02:07 Comparing Gen 3 to Today
02:30 - How Far We've Come
02:43 Text-to-Video 4.5: Gritty Film Looks
03:11 Gen 4.5 Image-to-Video: The Blue Suit Test
03:37 Testing Motion Blur & Consistency
04:08 How Gen 4.5 Explores Environments
04:18 Running Test: Speed & Physics
04:43 Novel Objects: The Tundra Hiker
05:37 The Bear Reveal Test
05:39 Camera Movements & Logic Failures
05:52 New Character Test: Nordic Warrior
06:12 The Viking Office Worker
06:27 Ghostly Monitors Experiment
06:51 Durations and Aspect Ratios
07:03 Sweeping Sci-FI Shots
07:23 Fantasy Test: Elf Princess
07:42 The "Walk and Talk" Consistency Check
08:08 Quality In Quality Out
08:36 Bringing it all together
08:47 Cyberpunk Woman Whip Pan
09:12 Zombie Apocalypse Helicopter Crash
09:31 Update Runway 4.5 Audio Features?
09:52 Runway UI Changes & Updates
10:21 Story Panels Explained
10:49 Generating Story Panel Outputs
11:05 Correction: The Panel Upscaler
11:22 Intro to Runway Workflows
11:34 Building a Node Graph
11:45 - Starting with a Flamethrower Girl Image
12:14 A/B Testing Shots in Workflows
12:37 The Extract Frames Feature
13:07 Final Thoughts on Runway's Ecosystem
Runway Gen 4.5 Image-to-Video is finally here, and it is a massive leap forward for AI filmmaking. In today’s video, we aren't just looking at the new model—we are stress-testing it. From character consistency and complex camera movements to how well it handles "novel" elements (like unexpected bears), we see exactly what Gen 4.5 is capable of.
We also take a stroll down memory lane to compare Gen 4.5 against Gen 3 and even the original Gen 1 to see just how far this technology has come. Plus, I catch you up on the massive UI updates, Story Panels, and how to use the powerful new Node-Based Workflows.
⚡ If you're NEW: Get 20% OFF RunwayML with this link: runwayml.com/?utm_source=creator&utm_medium=sponsored&utm_campaign=gen45&utm_content=theoretically-media
📩 Join my AI Newsletter for weekly tips & workflows: theoreticallymedia.beehiiv.com
IN THIS VIDEO: We explore the limits of the new Image-to-Video model, test the "Gritty Film" aesthetic in text-to-video, and fix the "paralysis" issues seen in previous generations. I also break down the new "Workflows" tab and show you how to properly use the Story Panel Upscaler to get high-res narrative shots.
CHAPTERS
00:00 Intro: Gen 4.5 Image-to-Video Release
00:28 Early Access
00:44 A Look Back
01:03 Revisiting Gen 2 Tests
01:16 Reviewing Gen 2 Output
01:44 Reviewing Gen 3 Output
02:07 Comparing Gen 3 to Today
02:30 - How Far We've Come
02:43 Text-to-Video 4.5: Gritty Film Looks
03:11 Gen 4.5 Image-to-Video: The Blue Suit Test
03:37 Testing Motion Blur & Consistency
04:08 How Gen 4.5 Explores Environments
04:18 Running Test: Speed & Physics
04:43 Novel Objects: The Tundra Hiker
05:37 The Bear Reveal Test
05:39 Camera Movements & Logic Failures
05:52 New Character Test: Nordic Warrior
06:12 The Viking Office Worker
06:27 Ghostly Monitors Experiment
06:51 Durations and Aspect Ratios
07:03 Sweeping Sci-FI Shots
07:23 Fantasy Test: Elf Princess
07:42 The "Walk and Talk" Consistency Check
08:08 Quality In Quality Out
08:36 Bringing it all together
08:47 Cyberpunk Woman Whip Pan
09:12 Zombie Apocalypse Helicopter Crash
09:31 Update Runway 4.5 Audio Features?
09:52 Runway UI Changes & Updates
10:21 Story Panels Explained
10:49 Generating Story Panel Outputs
11:05 Correction: The Panel Upscaler
11:22 Intro to Runway Workflows
11:34 Building a Node Graph
11:45 - Starting with a Flamethrower Girl Image
12:14 A/B Testing Shots in Workflows
12:37 The Extract Frames Feature
13:07 Final Thoughts on Runway's Ecosystem




![Octo Is Seedance’s Prompt Killer
Dreamina just rolled out Octo, a new canvas/agent workflow that tries to turn Seedance 2.0 into something closer to a scene builder than a prompt box.
So I tested it with character sheets, storyboards, a cyberpunk fight sequence, and a timeline extension to see whether Octo actually makes AI video workflows easier, or just moves the chaos into a new interface.
We’re also looking at NVIDIA Cosmos-3, Black Forest Labs showing Flux to Martin Scorsese, Bernini as an open-source “Google Omni for video” style model, and TripoSplat for turning 2D images into controllable 3D-ish spaces.
Basically: AI video is getting less like “write one prompt, get one clip” and more like planning, editing, world-building, and trying to keep the machine pointed in the right direction.
Big thanks to #genspark for Sponsoring Todays Video. You can get Free Credits at Genspark by using this link: https://www.genspark.ai/?utm_source=yt&utm_campaign=TheoreticallyMedia02
#WorkWithGenspark
Links:
Dreamina / Octo: https://dreamina.capcut.com/ai-tool/home?utm_source=Officiaaccount&utm_campaign=octo&utm_content=6ytb
NVIDIA Cosmos-3: [add link]
Cosmos-3 on FAL:
Black Forest Labs / Scorsese clip: https://x.com/bfl_ai/status/2061800769226252721?s=20
Bernini: https://bernini-ai.github.io/
TripioSplat: https://huggingface.co/spaces/VAST-AI/TripoSplat
CHAPTERS:
00:00 AI video workflows are heating up
00:24 Dreamina launches Octo
01:01 Using Octo as a canvas agent
01:51 Character sheets and storyboards
02:28 Where Octo starts to struggle
03:14 The Seedream / image model problem
04:03 Testing Octo with a cyberpunk character
04:28 The agent brain feels underpowered
05:27 Fixing the character sheet manually
05:56 Building the scene anyway
06:58 Turning the elements into video
07:35 Octo’s timeline extension
08:27 The part Octo actually nails
08:38 Is this the future of AI video workflows?
10:16 NVIDIA Cosmos 3
11:38 NVIDIA wants to be the physics department
12:21 Martin Scorsese meets Flux
13:03 Sponsor - GENSPARK
15:21 Bernini, an open-source Omni-style video model
16:23 How Bernini plans video edits
17:17 The H100 problem
17:49 Triple Splat turns images into 3D spaces
18:32 The cheap World Labs workaround
19:07 Wrap-up
#seedance2, #nvidia, #opensourceai Octo Is Seedance’s Prompt Killer](https://i.ytimg.com/vi/EmzS3MiXLfU/mqdefault.jpg)





