Uploaded November 2025 | Updated November 2026, 5 days ago
Black Forest Labs is back. FLUX 2 has officially dropped, and we’re finding out if it lives up to the hype or if it’s just a fresh coat of paint. Today, we’re putting Flux 2 through the wringer with deep testing on realistic textures, consistency, and the dreaded "hand" check.
Plus, the open-source video world gets a massive win with Hunyuan Video 1.5 (that doesn't require a mortgage to run), and a mysterious new challenger from Bytedance appears to take the crown.
In this video:
Full breakdown of Flux 2 features (4MP, JSON, Hex codes)
Side-by-side comparisons: Flux 2 vs. Reference Images vs. "Nano Banana"
First look at the lightweight Hunyuan Video 1.5
The mystery "Whisper Thunder" model climbing the leaderboards
🛑 Don't forget to subscribe for the latest AI workflows and theory!
LINKS:
Black Forest Labs: playground.bfl.ai/image/generate
Hunyuan Video 1.5: hunyuan.tencent.com/video/zh?tabIndex=0
Artificial Analysis: artificialanalysis.ai/video/models
⏳ Chapters
00:00 Intro & The Flux 2 Drop
00:37 The Timeline: From Flux 1 to Now
01:05 Flux 2 Features: 4MP & Hex Codes
01:49 Flux Flavors
02:14 The Area 51 "Blue Suit" Test
03:00 Checking Hands & Coffee Cups
03:30 The Pirate Tavern & Style Bias
04:07 Fixing Style with Image References
04:36 Character Consistency (The FBI Agent)
05:20 Multi-Reference Testing Setup
05:50 Comparison: Flux 2 vs. Nano Banana Pro
06:21 Glitch Check: The Third Arm
06:44 Testing the 180-Degree Rule
07:24 Complex Multi-Image Prompt Results
07:58 Community Showcases (Noir & Lighthouses)
08:36 Flux 2: The Initial Verdict
09:11 Hunyuan Video 1.5 Overview
09:46 Running Video AI Locally (14GB VRAM)
10:12 Bytedance's "Lab": The New Challenger?
10:42 Pose Reference: Bytedance vs. Banana
11:36 Mystery Model: Whisper Thunder
12:09 Text-to-Video Impressions
12:47 Outro & What’s Coming Next
Black Forest Labs is back. FLUX 2 has officially dropped, and we’re finding out if it lives up to the hype or if it’s just a fresh coat of paint. Today, we’re putting Flux 2 through the wringer with deep testing on realistic textures, consistency, and the dreaded "hand" check.
Plus, the open-source video world gets a massive win with Hunyuan Video 1.5 (that doesn't require a mortgage to run), and a mysterious new challenger from Bytedance appears to take the crown.
In this video:
Full breakdown of Flux 2 features (4MP, JSON, Hex codes)
Side-by-side comparisons: Flux 2 vs. Reference Images vs. "Nano Banana"
First look at the lightweight Hunyuan Video 1.5
The mystery "Whisper Thunder" model climbing the leaderboards
🛑 Don't forget to subscribe for the latest AI workflows and theory!
LINKS:
Black Forest Labs: playground.bfl.ai/image/generate
Hunyuan Video 1.5: hunyuan.tencent.com/video/zh?tabIndex=0
Artificial Analysis: artificialanalysis.ai/video/models
⏳ Chapters
00:00 Intro & The Flux 2 Drop
00:37 The Timeline: From Flux 1 to Now
01:05 Flux 2 Features: 4MP & Hex Codes
01:49 Flux Flavors
02:14 The Area 51 "Blue Suit" Test
03:00 Checking Hands & Coffee Cups
03:30 The Pirate Tavern & Style Bias
04:07 Fixing Style with Image References
04:36 Character Consistency (The FBI Agent)
05:20 Multi-Reference Testing Setup
05:50 Comparison: Flux 2 vs. Nano Banana Pro
06:21 Glitch Check: The Third Arm
06:44 Testing the 180-Degree Rule
07:24 Complex Multi-Image Prompt Results
07:58 Community Showcases (Noir & Lighthouses)
08:36 Flux 2: The Initial Verdict
09:11 Hunyuan Video 1.5 Overview
09:46 Running Video AI Locally (14GB VRAM)
10:12 Bytedance's "Lab": The New Challenger?
10:42 Pose Reference: Bytedance vs. Banana
11:36 Mystery Model: Whisper Thunder
12:09 Text-to-Video Impressions
12:47 Outro & What’s Coming Next






![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)



