dsh-image-vision
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.
141 results
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.
DSH web plugin: serve workspace image files over a constrained /dsh-image route so agents can embed images inline in conversation.
Umi-OCR vision bridge for DeepSeek Harness: when the main model is text-only, OCR images with local Umi-OCR and let the original DeepSeek model answer.
DSH tool plugin: generate images through ToAPIs async GPT-Image-2 API (submit task, poll, download).
DSH (DeepSeek Harness) Cordis plugin that lets the agent display images — local files or URLs — directly inside the conversation.
DeepSeek Harness plugin: drag images into the composer and get a file path back, so text-only models can read them via the read tool.
Keep native vision, drop historical images before they hit relay providers. Global DeepSeek Harness bundle for every agent.
Vision recognition plugin for DeepSeek Harness: paste images into the composer, recognize them via GLM-4V on the host side, and inject the result into the conversation.
Model-facing ocr_image tool that runs local RapidOCR (via a Python subprocess) and returns image text as plain text, so text-only DeepSeek models can read images
Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers
Lightweight DSH upload bridge: images and common documents become workspace paths so a text-only DeepSeek model can read them with Qwen-MM-Plugins vision tools.
DeepSeek Harness (dsh) plugin for wallpaper theming — upload images from the Settings page, pick one, and the whole dsh web UI renders over it with an adjustable readability mask and blur.
DSH 图片插件,三个工具覆盖三种场景:ask_user_choice 图片/图文混合选择卡(Web GUI 渲染,可放大查看)+ show_images 回复内嵌图片(图文混排)+ save_received_images 盲模型收图存为工作区文件;聊天栏所有图片点击放大,支持滚轮缩放与拖拽平移。来源支持本地路径 / http(s) URL / base64 data URI。零 token 本地渲染,纯插件实现不改核心包。
Image translation for non-multimodal models via GLM-4V-Flash: intercepts images, generates descriptions, injects as text.
dsh-std Community v0.15 ModelProvider: DeepSeek-V4-Pro with images captioned by V4-Flash-Vision-Exp. Requires @dsh-std/adapter-dsh on DeepSeek Harness.
Baidu cloud OCR (PaddleOCR-VL + Unlimited-OCR) for DeepSeek Harness Web: drag images/PDFs in, OCR to markdown, write results as local files.
Drag non-image files/folders into DeepSeek Harness web and insert their real absolute paths into the composer — no more "only images allowed". 拖拽工程文件/文件夹进 DSH,自动定位真实绝对路径插入输入框。
Preview images / SVG and CSV tables in the DeepSeek Harness chat, rendered as real browser <img> / <table> elements. Preview-first workflow: show the user the asset, wait for approval, then apply the real change.
Independent community DeepSeek Harness plugin for secure multi-file upload, native images, local document retrieval, and coordinate-aware text/PDF/DOCX/XLSX/PPTX reading.
DSH plugin: translate text-based PDFs via DeepSeek or any OpenAI-compatible API, preserving layout, fonts, images and links (editable output PDF, ≤50 pages per task).
DSH Web 输入框工具栏图片按钮:点击用系统文件选择器挑图片,不用拖拽。Toolbar button that opens the OS file picker to attach images to the DSH Web composer — no drag-and-drop needed.
Cyber Sand theme for DeepSeek Harness Web: a dark cyber-city palette (from the reference images) plus a background.
DeepSeek Harness plugin: analyse images out of band with a vision model — pasted images are digested into text before admission and a describe_image tool covers image paths, all without ever changing the session's model.
Convert model-bound images to JPEG/PNG/WebP for LM Studio compatibility