#23 · Primary category: Image Generation
infinite-canvas
面向 AI 创作的开源无限画布工作台,集成 AI 生图、参考图编辑、视频生成、Agent 智能助手、画布编排、对话创作、提示词库与素材管理等能力,支持可视化创作流程与多 Agent 协同工作。兼容 OpenAI 接口生态,支持 chatgpt2api、grok2api、flow2api、newapi 等渠道接入。
Project last updated:08/27/26
GitHub Stars
5.8K
Forks
1.5K
Contributors
14
License
MIT
Why we included this project
Infinite-canvas is a self-hosted workbench for image creation. Instead of moving between separate tools for prompting, reference editing, and asset storage, you stay on one board: drop a reference image onto a generation node, adjust the prompt, and retry until the composition works, with each run keeping the aspect ratio and logging the model, dimensions, and quality used. It plugs into the OpenAI-compatible endpoints you already pay for, so you bring your own API keys and channels rather than signing up for a hosted account. A local canvas agent works with Codex over MCP, so you can drive board edits from a chat panel without letting the web server touch browser state. The project is still in active development and frontend-first, so it rewards people comfortable maintaining their own deployment. Teams that need a stable turnkey product should probably hold off for now.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.