ATTENTION IS ALL YOU NEED
The most complex AgenC video yet.
• 26 hours 51 minutes, from the first lyrics to the final file
• 10.1 billion tokens
• 131 agents, 23,354 model calls
Music
• Piano written by me, the melody inspired by "Gouryella" by Gouryella
• Finished in Suno
Models (local and remote)
• Claude Opus 5.5
• Grok 4.7
• Grok Imagine Image 2.0 and Grok Imagine Video 1.5
• Qwen-Image 2.1
• Qwen-Image-Edit 2511
• Seedance 2.5
• MiniMax H3
• GPT Image 2.5
• GPT-2 XL (the attention and prediction data on screen)
• An SI model trained from scratch for the film (51M weights, 28,000 steps)
• BiRefNet (mattes), Depth Anything (depth), RAFT (optical flow), face and people detection
Tools
• AgenC Core
• ComfyUI
• Grok Build + Grok Bot
• Claude Code
• Blender Cycles (11 3D sequences)
• Python, Skia, PyTorch on CUDA
• ffmpeg with NVENC
The film
• 5:26 at 1920x1080, 24 fps
• 84 shots, 573 sung words on screen
• 12 new effect packages, 29 designed transitions
Hardware
• RTX PRO 6000 Blackwell
• RTX 5090
• 64 cores
• 1 TB RAM (8 x 128 GB)
Art, video & music
26-hour, 131-agent music video Attention Is All You Need
Tetsuo made 'Attention Is All You Need', a 5:26 music video with 84 shots, 573 sung words, and 29 designed transitions. The production ran 26 hours 51 minutes, used 131 agents, 23,354 model calls and 10.1 billion tokens across Claude Opus 5.5, Grok 4.7, Seedance 2.5 and others.
1.7Klikes
280reposts
662saves
62Kviews
- Made with
- Claude Opus 5.5, Grok 4.7, Seedance 2.5, Qwen-Image 2.1, MiniMax H3, GPT Image 2.5, ComfyUI, Blender Cycles, Claude Code
- Posted
