shanliuling/dsh-image-gen
Native conversational image generation for DeepSeek Harness: ask the agent to create an image, and it handles generation and keeps the result directly in the conversation.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run todayon DeepSeek Harness 0.2.2-rc.1.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.2-rc.1, today.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — Plugin for conversational image generation in DeepSeek Harness.
Who it is for — Developers using DeepSeek Harness for conversational tasks who require image generation with models like Gemini or OpenAI are suitable to install this plugin as it handles generation and keeps the result directly in the conversation. Users who do not require local ComfyUI integration can opt for cloud-based providers.
Watch out — Sandbox test passed: installed in fresh profile and registered successfully in profile. No other issues found.
The verdict — I would not install it because although it supports conversational image generation, the premise is already having other image generation services.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
dsh-image-gen is a DeepSeek Harness plugin that adds conversational image generation, editing, and image-focused creative workflows. DeepSeek Harness passes natural-language prompts, uploaded reference images, and follow-up edits to the configured image provider; generated results remain in the current conversation and can also be managed through the canvas, Studio, inspiration library, and gallery. Configuration is provided through the plugin detail page, where the provider, API key, model, Endpoint / Base URL, and workspace storage option can be set. Supported paths include cloud providers, subscription-based access, and a local ComfyUI service with an imported API Format Workflow JSON.
DeepSeek Harness users can use it for text-to-image, image-to-image, multi-image references, continuous revisions, batch generation, and comparing several models with the same prompt. Results may be stored with workspace isolation, while inspiration images are cached locally. The terminal surface is involved because installation is performed through a terminal command, and the README describes asking the agent to execute that command.
This is a poor fit for installations that only need basic chat functionality, cannot provide a supported provider credential or subscription, or cannot make a ComfyUI service reachable from the DeepSeek Harness host. The README requires a stable DeepSeek Harness release and Node.js ^22.19.0 or >= 24.0.0.
After restarting DeepSeek Harness, open the plugin panel and select dsh-image-gen under the installed plugins. DeepSeek Harness exposes a configuration form for the following settings:
ProviderAPI KeyModelEndpoint / Base URLThe form includes Test connection and Fetch models actions. Cloud providers can be configured with a provider-specific API key. ChatGPT, Grok, and Google subscription providers can instead be authorised through the provider’s Login action in a browser. The README does not specify default values for these settings.
For local ComfyUI use, enter a service address reachable from the DeepSeek Harness host and import an API Format Workflow JSON.
DeepSeek Harness sends conversational requests to the configured image provider. The plugin supports text-to-image, image-to-image, multiple reference images, style transfer, and revisions based on an existing prompt. A generated image can be regenerated in place, with earlier versions available from the same image card.
The canvas accepts sketches, reference material, recent results, and gallery images. Studio provides batch generation, provider and model selection, aspect-ratio and resolution controls, and result filtering. The comparison view calls multiple models with the same prompt and references. The gallery supports searching, favouriting, downloading, and reusing results. Inspiration examples can be copied or sent to Studio; their images are cached locally.
DeepSeek Harness must be on a stable release. The README lists Node.js ^22.19.0 or >= 24.0.0 and support for Gemini, OpenAI / Compatible, Seedream, DashScope, Grok Imagine, GLM-Image, and local ComfyUI.
Provider access, subscription authorisation, or a reachable ComfyUI service is required before generation. Installation uses a terminal-facing plugin command, so the agent may need terminal access for setup.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
loopx-project
LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
huangruiteng
LoopX, a provider-neutral, local-first state kernel and control plane for long-horizon agents: keeps Goal, Todo, gate, evidence, quota, recovery, and handoff state above DeepSeek Harness, while the plugin bootstraps the CLI and skills, admits bounded same-session continuation, and adds a loopback GoalBar for the exact bound loop.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
Q00
Config-only bundle that mounts Ouroboros through the DSH MCP client, exposing 36 interview, Seed, execution, evaluation, and evolution workflow tools in DSH.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
chuspeeism
Embeds the active installed Codex Taskboard runtime in the DeepSeek Harness sidebar, using its launcher runtime descriptor instead of a fixed port.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.
EthanYoQ
Installs a dedicated AI novel-writing preset and workbench: revisioned local project assets, a compact side drawer, and native approval-gated single-file changes.
No one-line install — this plugin lives inside a larger repository and publishes no npm package.