Uploaded June 2025 | Updated November 2026, 5 days ago
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
LINKS:
Krea: krea.ai
VEO-3 JSON Prompt Video: youtu.be/Azc4PzBPzcE
RECRAFT Infinite Styles Video: youtu.be/YUq71G0wazs
DreamStream Beta Signup: https://dreamcomputing.live/
Topaz Astra: topazlabs.com/ref/2518
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 Astra
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
LINKS:
Krea: krea.ai
VEO-3 JSON Prompt Video: youtu.be/Azc4PzBPzcE
RECRAFT Infinite Styles Video: youtu.be/YUq71G0wazs
DreamStream Beta Signup: https://dreamcomputing.live/
Topaz Astra: topazlabs.com/ref/2518
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 Astra










![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)