At a glance
What it does
Generate and process images in DeepSeek Harness through cloud, subscription, or local image backends.
Web Profile
Not declared in supplied evidence
Evidence-verified
Checked Sep 6, 2026, 1:51 PM UTC
Code-evidenced contributions
What it adds to DSH
Adds generation, background removal, upscaling, vectorization, blending, image comparison, and quality-inspection tools to DeepSeek Harness.
Mechanism evidence ↗Declares a web client and documents inline image display plus localized settings support.
Mechanism evidence ↗Before you choose it
A DeepSeek Harness web-profile bundle that adds tools for image generation and visual processing. It supports provider selection for FAL, Replicate, OpenAI-compatible APIs, ChatGPT/Grok subscriptions, local ComfyUI or Automatic1111, SeaDream, and Gemini; generated images can appear inline in the conversation.
Best for
DeepSeek Harness users who want agents to create, transform, compare, or inspect images from a chat workflow.
Common tasks
- Generate images with prompts, seeds, aspect ratios, and style presets.
- Remove a background, upscale an image, convert raster artwork to SVG, or blend reference images.
- Render an image pack in multiple aspect ratios, compare images, or inspect image sharpness and defects.
Permissions and data
The bundle can use configured image-generation services and local image servers.
Permissions- Uses DeepSeek Harness tools, attachments, credentials, settings, LLM, system-prompt, and webserver peer packages.
- Provides a web client integration for the Harness web platform.
- Prompts, image references, and generation parameters may be sent to the selected external provider or compatible endpoint.
- Local ComfyUI or Automatic1111 backends are documented as alternatives.
- FAL.ai, Replicate, OpenAI-compatible image APIs, ChatGPT/Grok subscriptions, SeaDream, and Gemini are documented options.
- Provider API access may be needed; the documented ChatGPT and Grok subscription options use OAuth.
Limitations
- No DeepSeek Harness version range is declared in the supplied evidence.
- Registry package contents were not audited.
- Actual installation, provider authentication, image output quality, and runtime behavior were not executed for this record.
- The MIT license provides the software without warranty.
What DSHub checked
- The immutable Git source commit, package structure, DSH bundle patch, npm package identity, MIT license, and Node.js >=20 engine declaration were captured.
- The manifest declares a web-platform client and required DeepSeek Harness peer dependencies.
What DSHub did not check
- Successful installation in a DeepSeek Harness profile.
- Provider credentials, OAuth flows, external API charges, and local-server connectivity.
- The README's performance, caching, fallback, and image-quality claims.
Pinned install
Install DSH Image Gen
This plugin bundle does not have a DSH Plugin install action. Use its source documentation for the delivery method.
Maintainer source
Project README
📦 @goodandready/dsh-image-gen
<div align="center"><h3>Comprehensive Visual Generation & Image Processing Suite for DeepSeek Harness</h3><p align="center"> <a href="https://www.npmjs.com/package/@goodandready/dsh-image-gen"><img src="https://img.shields.io/npm/v/@goodandready/dsh-image-gen.svg?style=for-the-badge&color=6366f1&labelColor=1e1b4b" alt="npm version"></a> <a href="LICENSE"><img src="https://img.shields.io/github/license/GooDAnDReaDY/dsh-image-gen.svg?style=for-the-badge&color=10b981&labelColor=064e3b" alt="license"></a> <a href="https://github.com/topics/dsh-plugin"><img src="https://img.shields.io/badge/DSH-Plugin-8b5cf6.svg?style=for-the-badge&labelColor=2e1065" alt="DSH Plugin"></a> <a href="https://nodejs.org"><img src="https://img.shields.io/badge/Node-20%2B-f59e0b.svg?style=for-the-badge&labelColor=451a03" alt="Node version"></a> </p><p align="center"> <a href="https://goodandready.app/"><img src="https://img.shields.io/badge/All_Author_Projects-goodandready.app-ff4500.svg?style=for-the-badge&logo=rocket&logoColor=white&labelColor=1a1a2e" alt="All Projects"></a> </p><p align="center"> <a href="README.md"><b>🇬🇧 English</b></a> • <a href="README.ru.md"><b>🇷🇺 Русский</b></a> • <a href="README.zh.md"><b>🇨🇳 中文说明</b></a> </p></div>⚡ Overview
@goodandready/dsh-image-gen is a premier graphic generation and visual processing suite for DeepSeek Harness. It equips autonomous agents with an extensible set of tools for image generation, transformation, background removal, upscaling, vectorization, multi-reference blending, and quality inspection across 8 generative backends.
🛡️ Reliability, Performance & Quality (v0.10.0)
- Exponential Backoff with Jitter: Adaptive polling for FAL, Replicate, and ComfyUI queues protects against HTTP 429 rate limits.
- Error Classification in Fallback Cascade: Client-side errors (Content Policy, 400 Bad Request, NSFW) fail fast without wasting API credits on other providers.
- Deterministic Hash Caching: Exact matches of prompt, model, and seed return instantly from local storage with zero API expense.
- ComfyUI & Automatic1111 Drag-and-Drop: Metadata is packed into PNG
Parameterschunks in standard format. - Dimension Snapping: Automatic normalization to multiples of 64 guarantees VAE bucket compatibility.
- Enhanced Style Presets: Built-in styles include tailor-made negative prompts and optimal guidance scale settings.
🛠️ Complete Tools Reference
generate_image: Generate images with pluggable providers, seeds, aspect ratios, and style presets.remove_background: Extract subject with transparent PNG output (FAL BiRefNet / Rembg).upscale_image: 2x / 4x super-resolution with clarity reconstruction.vectorize_image: Convert raster graphics to clean scalable SVG vectors with palette quantization.blend_images: Multi-reference composition mixing.generate_image_pack: Simultaneous multi-aspect ratio rendering with graceful partial recovery.compare_images: Pixel-level visual difference ratio comparison.inspect_image_quality: Automated visual audit, Laplacian sharpness scoring, and defect detection.
🚀 Updates in v0.10.4: Cordis Lifecycle, Full Settings GUI, and i18n
- Cordis Lifecycle (#136): wrapped all 7 tool registrations in
ctx.effectfor proper disposal on reload. - Settings GUI Completeness (#137): exposed fields for Replicate, SeaDream, Gemini, Local ComfyUI/A1111, style presets, and LLM enhancer.
- Package Manifest (#138): declared kernel
peerDependencies(host-webserver,settings,llm,system-prompt). - React Cleanup (#139): removed dead state hooks from
FalImageCard. - Complete Localization (#140): eliminated hardcoded strings, wiring comprehensive dictionaries for en, ru, and zh.
🎨 Supported Generation Backends
fal(Default): FAL.ai queue for FLUX.1, SDXL, Clarity Upscaler, and BiRefNet.replicate: FLUX and SDXL models via Replicate API.custom: OpenAI-compatible endpoint (DALL-E 3, SiliconFlow, Together AI, local gateways).codex: ChatGPT Plus/Pro subscription generation viadsh-subscriptions(OAuth).grok: Grok Imagine subscription generation viadsh-subscriptions(OAuth).local: Local ComfyUI workflow execution or Automatic1111 web API.seedream: ByteDance SeaDream generative API.gemini: Google Imagen 3 via GenAI API.
📦 Quick Installation
dsh plugin --profile web add @goodandready/dsh-image-gen
📄 License
MIT © GooDAnDReaDY
Operate deliberately
Install and manage
Prerequisites and target Profile
Target: Web Profile
Delivery: Dsh Bundle Git — GooDAnDReaDY/dsh-image-gen#47269c7371f66e8efc938412614587261ef12721。
Verify, update, and remove
Show lifecycle commands
dsh plugin --profile web listCompatibility and access
DeepSeek Harness web Profile bundle; Node.js 20 or later required: Not declared in supplied evidence。
Review compatibility evidence ↗
Risk facts
May send generation requests to selected cloud providers or a configured compatible endpoint.
Evidence ↗Some providers use API access; subscription-based ChatGPT and Grok options are described as OAuth-based.
Evidence ↗Evidence and editorial reviewManifest, Bundle patch, distribution and freshness
Immutable evidence
Review status and source activity
Use a provider and data path appropriate for the images and prompts you intend to send.
AI reviewed Sep 10, 2026, 11:36 AM UTC。GitHub facts last checked Sep 10, 2026, 11:36 AM UTC。
No material source change has been recorded since this evidence baseline.