Deploy Now

Stars

906

Forks

144

Watchers

2

Developer links

ima2-gen

ChatGPT, Grok, Gemini, NovelAI, and ComfyUI sit behind one prompt composer in ima2-gen, a studio that branches favorite AI images into variants and keeps every image and video in a searchable gallery. Multimode fires several candidates from one prompt and fills the slots as they finish, with up to five reference images attached. In the node graph a favorite grows into gold, marble, or forest variants that each remember their parent, so the original is never overwritten. Canvas Mode annotates, erases, and cuts out backgrounds, verifies GPT transparency from the decoded bytes, then exports PNG, SVG with an embedded raster, or traced vector paths. Grok video models turn text, one image, or a set of references into clips, and Storyboard mode keeps characters and scenes consistent across frames. Further lanes reach AtlasCloud, MiniMax, and MCP-connected Runway and Higgsfield, and each job goes only to the provider you choose. A prompt library imports packs from local files or GitHub folders, Prompt Builder refines rough ideas, and the gallery stores each render with its prompt, timing, and settings. A CLI and three Markdown skills let coding agents generate assets, vectorize logos, and run video jobs against the same studio. Binding to a network address requires an access token. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

ima2-gen
ima2-gen
ima2-gen
ima2-gen
ima2-gen

Benefits

  • Keep every render on your server
  • Images and video land in a local gallery with prompts, timing, and settings stored beside them, and prompts and references reach only the provider you choose for each job.
  • Switch providers without switching tools
  • One composer routes jobs to OpenAI, Grok, Gemini, NovelAI, ComfyUI, AtlasCloud, or MiniMax, so you can compare models side by side without learning a new interface each time.
  • Branch ideas without losing originals
  • The node graph links every variation to its parent image, so you can push a good result in several directions at once and never overwrite the source.
  • Hand the studio to coding agents
  • A full CLI and three Markdown skills let coding agents generate assets, vectorize logos, and run video jobs against the same local server you use in the browser.

Features

  • Multimode generation
  • Launch several candidates from one prompt and watch them fill slot by slot, with up to five reference images attached and large references compressed before upload.
  • Canvas Mode
  • Annotate, erase, cut backgrounds, and export with alpha or a matte color; GPT transparency is verified from decoded bytes, and Trace to SVG flattens art into vector paths.
  • Grok video lanes
  • Text-to-video, image-to-video, and reference-to-video through Grok video models, with live progress, native 1080p on Grok video 1.5, and Storyboard mode for consistent characters.
  • Ten provider lanes
  • OpenAI OAuth and API, Grok, Gemini and Vertex, Antigravity CLI, NovelAI, ComfyUI workflows, AtlasCloud, and MiniMax, plus MCP-backed Runway and Higgsfield integrations.
  • CLI and agent skills
  • The ima2 CLI covers gen, edit, video, vectorize, and history, and ima2 skill installs Core, Frontend, and UI/UX Markdown skills into an agent's skills directory.
  • Prompt library and Builder
  • The library imports local packs and GitHub folders into a searchable index, while Prompt Builder refines intent through the GPT, Grok, or API text backend you pin.

Apps Similar to ima2-gen