← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-qwen-paint

DeepSeek Harness plugin enabling offline image generation via local ComfyUI and Qwen-Image 2.1.

VisionUI & ProductivityTerminal & TUIDeveloper ToolsSkills & Workflows
6GitHub Stars2ForksUpdated2026-10-08

Install

$ 或等价 CLI dsh plugin --profile desktop add link:<本目录>(**desktop profile 必须先完全退出 DSH**)。

Plugin Overview & Capabilities

AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.

source-grounded
dsh-qwen-paint connects DeepSeek Harness to a local ComfyUI instance running the Qwen-Image 2.1 model. Operating entirely over localhost (127.0.0.1) without external network calls or API keys, it registers a `draw_image` host tool, displays rendered images directly within the conversation via client slots, provides an idle auto-shutdown mechanism to preserve GPU memory, and docks a ComfyUI status indicator under the composer.

Key Capabilities

  • Registers the `draw_image` tool supporting prompts, aspect ratios, step counts, and seeds
  • Generates images offline via local ComfyUI with no external API keys required
  • Renders generated outputs directly inside chat rows using custom toolview and Markdown references
  • Automatically terminates idle ComfyUI processes after 5 minutes of inactivity to conserve VRAM
  • Displays real-time ComfyUI service status below the chat composer dock
  • Provides automated setup and verification scripts for ComfyUI and model weights

Useful For

  • Local text-to-image generation directly within DeepSeek Harness conversations
  • Private, offline AI artwork creation without third-party cloud costs or API quotas
  • Managing GPU memory overhead during local AI workflows via automated idle shutdowns

Who It Fits

  • DeepSeek Harness desktop users with local GPU setups (NVIDIA or AMD ROCm)
  • Developers and creators running local ComfyUI pipelines for privacy-first image synthesis

Documented Limitations

  • Requires a local ComfyUI installation and approximately 13.3 GB of Qwen-Image model weights
  • Demands dedicated GPU resources; Intel integrated GPUs are insufficient, and VRAM swapping can slow generation on lower memory cards
  • Negative prompts have minimal impact due to CFG=1 behavior on the Qwen model
  • DSH desktop app must be restarted after bundle installation for host tools to be loaded

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

Dependency Counts

package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
wonderandyou/dsh-qwen-paint
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
ef86e5a · 2026-10-21

This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.

Repository Activity

GitHub stars
6GitHub stars
Forks
2
Open issues
0
Last commit
2026-10-08
Last release
2026-10-08
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app