@dsh-extension/dsh-generation-image
On-demand image generation for DeepSeek Harness (DSH): a generate_image tool that calls your own OpenAI-compatible image URL + API key and delivers the image into the session
462 results
On-demand image generation for DeepSeek Harness (DSH): a generate_image tool that calls your own OpenAI-compatible image URL + API key and delivers the image into the session
DeepSeek Harness Artifact/Deliverable plugin: publish workspace files as chat artifacts with inline image previews and download cards.
Dynamically change DSH Web CSS from Settings: raw CSS, background image, and a user JS file.
Connect an official Grok subscription to DSH as an ACP subagent, extending its native image support with audio and video tools.
Create production-ready AI image prompts and image descriptions with the Find Image Prompt image-to-prompt API.
DSH plugin: auto-downscale oversized images (and a portable Agent Skill). Powered by sharp. Install from GitHub — no npm publish.
DeepSeek Harness plugin: text-to-image output with in-chat image cards, download button, history gallery, and provider selection tabs
聊天输入框图片工具(自研):上传图片(≤10MB 防烧 token) + 自定义区域截图(Electron desktopCapturer),注入 DSH 草稿图片轨。零外部依赖。
A Genshin Impact Columbina (哥伦比娅) themed plugin for DeepSeek Harness Web: preset/custom background images with a translucent mask, per light/dark scheme palettes, and a special glow for the active conversation title.
Use local Wallpaper Engine images, videos, and scene textures as the DeepSeek Harness web background
DeepSeek Harness (DSH) native plugin: the describe_image tool, a vision bridge (image -> mimo-v2.5 -> text description) over the ctx.fs / ctx.credentials seams
Right-side collapsible panel for dsh web: list, copy and clean images uploaded via DeepSeek Files API
VS Code-style file explorer plugin for the dsh web GUI: file panel beside the sidebar, multi-tab preview panel (code/images/PDF/audio/video/Markdown/CSV/Excel/Word/zip), filename search, sort/filter, copy-paste, swap sides and drag-resize — zero patches to official packages
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。
DSH host plugin: automatically sends images in user messages to a vision model (default mimo-v2.5 on opencode-go) and feeds the returned text description to the main text model (e.g. deepseek-v4-pro), without touching the visible chat transcript.
Persistent wallpaper skin for the dsh web profile: static image or muted looping video as the app background, with translucent panels. The path is editable live from Settings → Plugins.
Transparent image preprocessing route for DeepSeek Harness
Official Weixin iLink text, image, and file bridge for DeepSeek Harness
Codex-style artifact preview for DeepSeek Harness (DSH): produced-files row in chat with inline image thumbnails, and a resizable split-screen side preview panel rendering Markdown / source code / CSV / JSON / images / HTML, plus localhost port preview.
DeepSeek Harness tool for local image OCR with the WeChat OCR engine.
Point-and-shoot screenshot capture for DeepSeek Harness: clipboard watcher + system floating window (comment & key-point, copy/save-doc/save-image) + instant OCR + Obsidian per-day merging + evening AI organization. 指哪拍哪 · 截图即存:剪贴板监听 + 鼠标位置系统级悬浮窗 + 即时 OCR + Obsidian 按天合并 + 晚间 AI 整理打双链
Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.
Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images
Pixel-diff two screenshots into diff.png + a labeled triptych (pixelmatch)