Back to directory

iLab CONJURE

iLab CONJURE is a local-first, multi-model AI image generation workbench with a web UI and CLI, supporting GPT Image and Gemini models through official APIs or OpenAI-compatible providers.

iLab CONJURE

iLab CONJURE is a local-first workbench for generating and editing images with GPT Image and Gemini models, reachable through their official APIs, an OpenAI-compatible relay, or Codex's own image channels. It provides a shared image gallery, quick-reference chips, prompt templates, multi-task concurrency, and a paginated local history stored in SQLite with search, filtering, favorites, tags and bulk export to a ZIP archive.

Its image editor supports inserting reference images, layering multiple images, locked-ratio transforms, free transforms and local erasing. Generation settings can be locked and shown read-only so they are not changed by accident while browsing history or switching tasks. Network settings support system, direct or custom HTTP(S) proxies, with configurable request timeouts and retry counts.

It ships as a macOS DMG and a Windows app with a native tray launcher, and also provides a CLI for local automation. The project was previously named iLab GPT CONJURE.

More in Generative media

See all 146
  • Blender Copilot

    github.com

    A Copilot-style AI chat panel inside Blender that runs its agent loop in Blender's own Python process, executes the model's generated code against the live scene, and wraps every conversational turn in a single undo step.

  • A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

  • A ComfyUI node that expands a short prompt into a full styled prompt, negative prompt and aspect ratio for Qwen-Image-2.1, using one of 17 photographic styles.