kadevin/ilab-conjure

面向 GPT-image-2 的 AI 图片生成 WebUI 工作台，支持 Codex Responses 与 OpenAI 兼容 API 接入，内置公用图库、多类型 Chip 快捷引用、提示词模板、多任务并发和本地队列管理。An AI image generation WebUI workbench for GPT-image-2 with Codex Responses and OpenAI-compatible API support, shared gallery references, multi-type quick chips, prompt templates, concurrent tasks, and local queue management.

What it solves

It provides a unified, local-first workspace for generating and editing images using various AI models. It simplifies the complex workflow of managing multiple API providers, prompt templates, and image assets by consolidating them into a single interface.

How it works

The platform connects to image generation models via OpenAI-compatible APIs or through advanced local OAuth modes (like Codex/ChatGPT). It uses a WebUI to manage tasks, a local SQLite database for history, and a local file system for image libraries. It supports concurrent task execution, local queuing, and an integrated image editor for advanced manipulations.

Who it’s for

  • AI artists and designers looking for a centralized interface for multiple image models.
  • Developers needing a CLI for automated image generation tasks.
  • Teams requiring a stable, API-based workflow for shared workstations.

Highlights

  • Supports multiple models including GPT Image and Gemini.
  • Features a comprehensive image editor with layer support and local erasing.
  • Includes a local public library for reusable reference images and color chips.
  • Provides both a WebUI and a CLI for automation.
  • Supports concurrent task management and local queueing.
  • Offers specialized prompt templates and snippet management via 'chips'.