shanliuling/dsh-image-gen

AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.

What it solves

dsh-image-gen is a comprehensive AI image creation suite designed as a plugin for DeepSeek Harness (DSH). It bridges the gap between simple chat-based image generation and a professional creative workflow, providing tools for iterative editing, batch production, and multi-model comparison.

How it works

The plugin integrates with various cloud-based image providers (such as OpenAI, Google Gemini, and Aliyun DashScope) and local ComfyUI setups. It allows users to generate images via natural language in a chat interface, use an infinite canvas for sketching and iterative refinement, or use a dedicated Studio for precise parameter control and batch generation. It also supports "subscription-based" access, allowing users with existing ChatGPT, Grok, or Google subscriptions to generate images without needing separate API keys.

Who it’s for

Users of DeepSeek Harness who want a centralized hub for AI image generation, from quick conceptualization to high-fidelity production, supporting both cloud APIs and local GPU power via ComfyUI.

Highlights

  • AI Creative Canvas: An infinite canvas for sketching, combining reference images, and iteratively refining images through dialogue.
  • Studio Batch Creation: A dedicated workbench for batch generating candidates with fine-grained control over models, aspect ratios, and resolution.
  • Multi-Model Comparison: The ability to run the same prompt across multiple AI models simultaneously to compare results side-by-side.
  • Local ComfyUI Integration: Support for importing and managing multiple named ComfyUI workflows for private, local image generation.
  • Prompt Inspiration Library: A built-in collection of over 500 prompt examples for style exploration and one-click reuse.
  • Integrated Gallery: A unified system to manage, search, and organize generated images, isolated by workspace.

Related

  • Project
    hero8152/Infinite-Canvas

    A visual, infinite canvas workspace that integrates multiple AI APIs and local ComfyUI workflows for collaborative generative AI content creation.

  • Project
    Anionex/dsh-vision-toolkit

    A DeepSeek Harness plugin that equips text‑only agents with vision capabilities—OCR, object grounding, cropping, SVG tracing, pixel‑diff, and UI reconstruction—via a set of 10 tools and a bundled vision‑skills Skill. Install with one `dsh plugin` command, configure any OpenAI‑compatible vision model (default Gemini 3.7 Flash), then paste images and ask questions. The toolkit provides task‑aware image descriptions, local deterministic processing, and seamless integration into DSH Web, Headless, and Desktop profiles.

  • Project
    hust-open-atom-club/oh-dsh

    A unified runtime and workbench for AI agents that provides Desktop, Web, and TUI interfaces for managing local development tools and plugins.

  • Project
    Devin-AXIS/deepseek-design

    A native visual design system for DeepSeek Harness that allows AI to generate and manually refine editable websites, presentations, and videos.

  • Project
    waooAI/waoowaoo

    An AI creative workspace for images and videos that combines an AI assistant, a visual canvas for organization, and integration with various generative models.