Vision tools · DeepSeek Harness plugins — Page 46

DSH web plugin: set a background image and adapt the theme colors (background + text + brand + borders) to the image palette.

DeepSeek Harness plugin: an inline conversation image card with a bottom-left edit button (annotate / erase / resize) that hands the edit back to the agent.

DSH plugin that lets text-only (non-multimodal) models send and read images: bypasses the image admission gate, rewrites image blocks to local paths, and OCRs/describes them via configurable vision API providers (image_to_text tool).

图片处理：读取图片尺寸/格式、缩放与格式转换（内置 ffmpeg，跨平台）

DeepSeek Harness 原生插件：让纯文本模型（如 DeepSeek）经 agent/pre-step 劫持 + resolveModelInfo 包装自动识别上传图片（qwen-vl），使纯文本对话也能“看见”图片。

Zoom, pan, download, gallery, and region-note image viewer for DeepSeek Harness

Seamless image understanding for DeepSeek Harness: lets pure-text models read pasted/dropped images and Feishu/Lark images via a configurable vision model, without touching the host.

Image2 (gpt-image-2) generation plugin for DeepSeek Harness with simple relay settings, in-conversation previews, a chat-dock studio (text-to-image / image-to-image / multi-view character consistency) and a reusable prompt/flow preset library. Community fork of JuneLearn/dsh-image2-draw with gateway compatibility fixes.

image_gen and image_vision model tools for the DeepSeek Harness, powered by the ChatGPT subscription (no API key).

dsh 插件:图像生成/编辑/识图(imagegen + image_understand),provider 无关,默认提供方 Agnes AI(OpenAI 兼容)

Provider-neutral image generation tool for DeepSeek Harness

A DeepSeek Harness plugin that registers a generate_image tool (Qwen-Image / DeepSeek Janus-Pro-7B via SiliconFlow) callable by the model.

Bundled imagegen skill for DeepSeek Harness: generate or edit raster images (photos, illustrations, textures, sprites, mockups, transparent-background cutouts) from the agent, through any OpenAI-compatible GPT Image endpoint.

DSH image-generation plugin with native support for the zhenzhen-image async task gateway (POST /image/generations -> top-level task_id -> poll GET /image/generations/<id>): text-to-image and multi-reference image-to-image, no bridge process or external image host required. Forked from @dickpy/dsh-imagegen.

DeepSeek Harness plugin: text-to-image output with in-chat image cards, download button, history gallery, and provider selection tabs

Click-to-zoom lightbox for DSH conversation images with arrow-key paging: click any image card to enlarge, <- / -> to flip prev/next, Esc to close. Edge hints included.

Inline clickable image cards for DSH conversations: show_image tool + webServer image route + keyed toolview card

对话内联图片/视频:LLM 回复中输出的本地图片路径直接在消息正文内渲染为图片,视频以可点击播放链接呈现。支持图片URL自动修正与刷新持久化,兼容反向代理部署。

Persistent inline image, video, and audio previews for DeepSeek Harness Web conversations, with workspace-confined local reads and a configurable ComfyUI proxy.

即梦(火山方舟 Seedream)文生图/图生图插件:模型工具 generate_image / image_to_image + 设置面板可编辑 API 配置 + 手动生图面板

Jina AI tools for DeepSeek Harness: search (incl. arxiv/ssrn academic domains), read, screenshot, embed, rerank, classify, pdf, expand, datetime, primer — with a settings-page API key UI.

Jina AI tools for DeepSeek Harness: search (incl. arxiv/ssrn academic domains), read, screenshot, embed, rerank, classify, pdf, expand, datetime, primer — with a settings-page API key UI.

Kimi WebBridge for DeepSeek Harness: drive the user's real browser (navigate, click, fill, snapshot, screenshot, evaluate, network, upload, PDF) through the local Kimi WebBridge daemon

KoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.