#54 · Primary category: Image Generation

ima2-gen

ai-agent gemini grok image-generation local-first mcp node-editor openai video-generation visual-workflow

Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.

Project last updated:08/27/26

GitHub Stars

722

Forks

120

Contributors

13

License

MIT

Why we included this project

ima2-gen is a local-first studio for people and coding agents who want image and video generation without juggling several provider web apps. A single install gives you one CLI and web UI that reach OpenAI, Grok, Gemini, MiniMax, and other providers, so the same workflow stays reproducible no matter which backend you pick. It is built around iteration rather than one-shot prompts: you can branch a good result into new directions in node mode, batch several outputs from a single prompt, keep reference images attached, and clean up in a canvas that supports real alpha transparency. Video work covers both text-to-video and image-to-video, and because everything runs on your own machine with a local history, the CLI is scriptable enough for coding agents to drive generation as part of a workflow. Teams that want provider-agnostic generation without sending every asset to a hosted dashboard will find a practical fit here.

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