Stanford SVL's DyCraft generates minute-long multi-shot 3D Blender animations from text
songyoupeng · x · 2026-11-12
Stanford SVL introduces DyCraft, which uses an LLM to build minute-long 3D Blender animations from text prompts—each with dozens of shots and realistic motion for people, humanoid robots, animals, and mechanisms. More details in their thread.
More from Multimodal
- MiniMax H3 Image generates 3D game scenes in 10s, over 3x faster than GPT Image — HeyToha · 2026-11-12
- Ex-Meta CV researcher builds AdaL v2, a chat-driven video agent harness for GTM — Scobleizer · 2026-11-12
- MiniMax H3 image gen runs locally on AMD RX 9070, 25-30s per 4MP image — omglionheaded · 2026-11-12
- One reference, one prompt, three image models: side-by-side Nano Banana Pro vs GPT Image 2.6 test — gizakdag · 2026-11-12
- From one grumpy bear to a full brand: building an AI-generated bagel brand end-to-end in Figma Weave — gizakdag · 2026-11-12
- Gemini-built 3D amusement pier sim runs at 60 FPS with POV roller coaster — intellectronica · 2026-11-12