dsh-image-gen
dsh-image-gen is a plugin that adds image generation, editing and side-by-side comparison to the DSH agent app for people making visuals.
What it is good for
- Generating images from text descriptions inside a chat
- Editing and revising existing pictures through follow-up messages
- Comparing results from several image models side by side
- Running private image generation on your own graphics card
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Skill or plugin
- Tasks
- Works with
- DeepSeek Harness, ComfyUI, Google Gemini, OpenAI Images, ByteDance Seedream, Grok Imagine
Momentum
- Rank this week
- #93
- Best rank
- #93 week 44, 2026
- Stars gained last week
- +363
- GitHub stars
- 1,066
GitHub numbers as of Nov 2, 2026. Updated weekly.
Ranking history
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is dsh-image-gen free?
- Yes. It is free and open source (Apache-2.0 license).
- Do I need to know how to code to use dsh-image-gen?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does dsh-image-gen work with?
- According to its own documentation, it works with DeepSeek Harness, ComfyUI, Google Gemini, OpenAI Images, ByteDance Seedream, and Grok Imagine.
- What is dsh-image-gen good for?
- Generating images from text descriptions inside a chat, editing and revising existing pictures through follow-up messages, comparing results from several image models side by side, and running private image generation on your own graphics card.
Similar agents
- mono-color-skill
Monocolor Editorial Print is a skill that turns a theme, sentence, or photo into a one-ink or two-ink editorial print image for posters, zines, and packaging.
- skills
skills is a collection of agent skills that shoot cinematic UI videos and framed app screenshots for marketing and docs.
- awesome-gpt-image-2
awesome-gpt-image-2 is a prompt library and agent skill that helps users write reusable prompts for GPT Image 2 image generation.
- guizang-ppt-skill
guizang-ppt-skill is a skill that builds single-file HTML slide decks, cover images, and a presenter mode for people who create presentations with an AI coding agent.
- baoyu-skills
baoyu-skills is a set of skills that adds content creation and publishing abilities to Claude Code and Codex for daily writing and image work.
- GPT-Image2-Skill
GPT-Image2-Skill is a prompt library and agent skill that helps you generate and edit images with OpenAI's GPT Image models.