An open-source infinite canvas workbench for AI creation: image and video generation, reference-based editing, a chat assistant, prompt library and asset management in one interface. Works with any OpenAI-compatible API, with keys stored locally in the browser.
Useful for
- Build a node chain on the canvas for iterative image generation from text and references
- Connect your own OpenAI-compatible Base URL and API key for image and video generation
- Let a local agent drive the current canvas via MCP and insert results back
Before using
- License: MIT
- Installation and requirements have not been verified; review the README before running
Why now
- Created on GitHub
- 2026-05-18 UTC
- First seen by GitNova
- 2026-09-13 UTC
- Typical day
- +32 stars · median of 28 complete days
- Magnitude
- 7.4 / 10 · growing interest
This measurement does not yet confirm a daily spike over the usual gain
Maximum over those 28 complete days: +917 on 2026-10-23; the current measurement has not exceeded it (UTC)
Measured: October 24, 2026, 12:39 UTC
Measurement details
- Created on GitHub: 2026-05-18; first seen by GitNova: 2026-09-13 (UTC)
- +4 stars measured 2026-10-24, 11:42–12:29 UTC
- Usually: +32 stars/day — median of 28 complete days 2026-09-26–2026-10-23 (UTC)
- This measurement does not yet confirm a daily spike over the usual gain
- Maximum over those 28 complete days: +917 on 2026-10-23; the current measurement has not exceeded it (UTC)
- Magnitude 7.4/10