ComfyUI workflow: turn concept art into any-angle stills and camera moves with Tripo, GPT Image 2 and Seedance 2.0
petewoodbridge · x · 2026-09-18
ComfyUI officially released its 'Concept Art to Any Angle' animation workflow, chaining three tools in one graph:
- Step 1: Load concept art, generate a 3D model with Tripo and export as GLB, then drag into Load 3D with material mode set to Normal
- Stills: rotate the viewport to any angle; Load 3D outputs that view, and GPT Image 2 renders it back as a polished on-style illustration
- Camera moves: record a viewport path; that clip becomes the motion reference for Seedance 2.0, which generates the move through the stylized scene
The workflow is published via a runnable link, giving artists a reproducible pipeline from a single concept painting to multi-angle illustrations and camera animations.
More from coding & agent
- Dev bets OpenAI DevDay unveils a unified persistent agent in the mold of Muse — brandon_galang · 2026-09-18
- Perplexity rolls out effort controls in Computer; user shares a 3-tier model workflow — inductionheads · 2026-09-18
- 48 hours old, 724 ads broken down in 40 seconds: Jev sweeps the dev world — Scobleizer · 2026-09-18
- Nebula launches multiplayer AI workspace where agents live in team channels — Scobleizer · 2026-09-18
- Running multiple harnesses at once is the key agent skill: Claude Code, Codex, Fable, DeepSeek combo — EXM7777 · 2026-09-18
- TypeSafe's structured evaluation model Jev goes live on Cloudflare AI Gateway — michellechen · 2026-09-18