dsh-image-gen: Native In-Chat Image Generation and Editing Plugin for DeepSeek Harness
shanliuling/dsh-image-gen
dsh-image-gen brings native in-chat image generation and editing to DeepSeek Harness, supporting multiple providers and local ComfyUI with a built-in gallery.
dsh-image-gen adds native image generation and editing to DeepSeek Harness conversations, letting agents produce images directly in chat. It supports text-to-image, image-to-image, and multi-turn iterative editing, and connects to backends like Gemini, OpenAI, Seedream, DashScope, and local ComfyUI. All historical images are automatically collected into a gallery for easy search, preview, and management. With it, you can ask DSH to draw and keep refining in natural language without leaving the conversation.
How to Install
dsh plugin --profile web add dsh-image-gen- Category
- Tools & Capabilities
- Platform
- DSH Plugin
- Author
- shanliuling
- Distribution
- Plugin
dsh-image-gen Key Features
dsh-image-gen Repo Summary
What Does It Do?
dsh-image-gen is a DSH plugin for DeepSeek Harness that adds native image generation and editing capabilities to DSH conversations. It solves the problem of agents not being able to produce images directly in chat, letting you generate, edit, and manage images using natural language. Core capabilities include text-to-image, image-to-image, multi-turn iterative editing, gallery management, and support for multiple backends such as Gemini, OpenAI, Seedream, DashScope, and local ComfyUI.
Core Features
- Native in-chat generation and editing: generate images directly in DSH conversations and modify existing ones.
- Multi-turn iterative editing: reuse uploaded images, historical generations, and previous edit results in the same session.
- Gallery and image tools: automatically collect historical images with search, filter, fullscreen preview, copy, download, and delete.
- Multi-provider support: compatible with Google Gemini, OpenAI Images / Compatible, ByteDance Seedream, Aliyun DashScope, and local ComfyUI workflows.
- BYOK and native settings: configure API keys, providers, models, and endpoints directly in DSH settings.
- Session and workspace saving: images integrate with DSH Attachment / Conversation and auto-save to the current workspace.
How to Use This Plugin?
After enabling the plugin in DSH, go to Settings → Plugins → Image generation to configure a provider: for cloud services, enter your API key; for local ComfyUI, provide the address and import an API Format Workflow JSON (use {{prompt}} for the prompt placeholder and optionally {{seed}} for the seed). Once configured, simply type something like "generate a cyberpunk cat on a rainy neon street" in the chat, and the agent will call the generation tool and return the image in the conversation; if you say "add floor-to-ceiling windows to the last image," the agent will edit the previous image. All historical images can be viewed and managed in the "Gallery" tab at the top of the conversation.
This page is an independent rewrite of the plugin's official README — for authoritative documentation and the latest changes, refer to the source: shanliuling/dsh-image-gen. The plugin is third-party code that runs on your machine once installed; inclusion does not imply endorsement — please review the source before installing.