Generate images through a logged-in web ChatGPT session and download them to a local directory.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:CAI-MH/dsh-gpt-image
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
This plugin publishes its README in Chinese only.
控制已登录的网页版 ChatGPT 生成图片并下载到本地的 DSH 插件：注册
gpt_generate_image 工具，复用 Edge 调试端口（9222）里的 ChatGPT 会话生成图片。
文件
index.js— Host 半部分：注册gpt_generate_image工具 + 生图行为系统提示词cordis.patch.yml— host 组合插件行（id:gpt-image）package.json— bundle 元数据
依赖的全局资源（不在本 bundle 内）
生图脚本 gpt-image.mjs（含 puppeteer-core 依赖）、ensure-edge-debug.sh、
start-edge-debug.sh 及 Edge 调试 profile，均位于脚本目录（默认
~/work/dph/）。生成图片下载到当前会话工作区的 figures/gpt_generated/。
配置与迁移（重要）
默认脚本目录为 ~/work/dph。若要迁移脚本与 Edge 资源目录，
不要改本 bundle 源码，改 web profile 的补丁配置：
~/Library/Application Support/dsh-desktop/harness/profiles/web/cordis.patch.yml
- id: gpt-image
config:
workspace: ~/work/dph
把 workspace 改成新目录后重启 DSH Desktop 即可。
安装与生效
bundle 注册在 web profile 的 package.json（dependencies + dsh.profile.bundles），
node_modules 内为副本。改代码要改本目录再重新拷贝进 node_modules，然后重启 DSH Desktop。
Links
More in this category
zhu1090093659/dsh-web-ui#packages/dsh-tool-describe-image★ 7749
A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.
liustack/modlens★ 3985
Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).
ysr666/dsh-vision-router★ 1108
Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.
Anionex/dsh-vision-toolkit★ 882
Vision for text-only models: paste an image and the model switches to a Vision Toolkit variant for image Q&A, multi-image comparison, long-screenshot OCR, screenshot-to-UI reproduction, element grounding, and pixel diff. No API key by default — images are processed by the author-hosted free service, 100 per machine per day; configurable to your own provider.
dickpy/dsh-imagegen★ 79
AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.
fandc520/dsh-comfyui★ 74
Drive a local or remote ComfyUI server from DeepSeek Harness: comfyui_run / comfyui_object_info / comfyui_workflow tools generate and edit images and videos, with a workflow library (graph extraction: per component / main flow / all), a load area with resolution auto-match, a live queue, SDXL and Wan 2.1 templates, a companion skill, and a same-origin media proxy.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.