Canvas-to-Image turns identities, poses, and boxes into one RGB canvas
CSProfKGD · x · 2026-07-23
At SIGGRAPH 2026, Yusuf Dalva is presenting Canvas-to-Image (C2I), a new multimodal image-generation control paradigm built around a single RGB canvas.
The idea is to put all controls in one intuitive surface instead of juggling separate interfaces:
- specify identities, poses, and bounding boxes directly on the canvas
- let the system interpret the design and generate the image faithfully
- position the workflow as a compositional-control interface for creators
The post links the work to image-generation research and to multimodal control in general.
More from Multimodal
- Full animation short made with Google Gemini tools, 10,564 frames — AI_Andrew · 2026-10-26
- ostris pre-training "Primal VAE": 1-channel latents match modern 8x VAEs via patching — ostrisai · 2026-10-26
- Slopcore: AI-generated meme films turn low-fi slop aesthetics into a subculture — Yamapama · 2026-10-26
- TischEins, a large Midjourney SREF library, relaunches with new design after security outage — tisch_eins · 2026-10-26
- MOSS-Image-SFT 4-step distillation tops 16.5K downloads on Hugging Face — _akhaliq · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26