@xiaoyuink/dsh-image-vision
图片识别插件:自动判断当前模型是否具备视觉能力,有则用当前模型并按插件预设提示词分析,无则调用插件配置的视觉模型。文本模型可直接在对话框粘贴/上传/拖拽图片,发送时自动写入 DSH 附件存储(永久),消息区渲染缩略图,模型自动调用 image_vision / ocr / ground / crop 系列工具识别与精读;模型选择器保持简洁。
749 results
图片识别插件:自动判断当前模型是否具备视觉能力,有则用当前模型并按插件预设提示词分析,无则调用插件配置的视觉模型。文本模型可直接在对话框粘贴/上传/拖拽图片,发送时自动写入 DSH 附件存储(永久),消息区渲染缩略图,模型自动调用 image_vision / ocr / ground / crop 系列工具识别与精读;模型选择器保持简洁。
DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.
Renders images, video, audio, PDF and Office documents inline in the dsh web UI through a display_file tool, streaming bytes over a signed HTTP route with range support.
WaveSpeed skill for DeepSeek Harness (dsh): generate and edit AI media (image, video, audio, 3D) via the open-source wavespeed CLI.
DSH web plugin: a status bar at the bottom of the conversation showing the estimated API cost of the current session (per-model token pricing, CNY) plus the live DeepSeek account balance queried through the official balance API.
Usage (用量) deployment plugin for DeepSeek Harness (DSH): a real-time token & cost dashboard tab next to chat/trajectory, with live streaming estimates, DeepSeek official peak/off-peak pricing and OpenCode Go plan pricing, custom price table, and CSV/JSON export.
External vision proxy plugin for DeepSeek Harness, enabling text-only models (DeepSeek-V3 / R1) to analyze and understand images via OpenAI-compatible vision APIs.
DSH Pet Corner: a floating pet, keyless pet-image proxy, favorites, and plugin-owned settings API
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
桌宠小鲸鱼:随 agent 状态切换动画的 DeepSeek Harness Web 桌宠插件(官方轮廓版)
Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.
??pro -- DeepSeek Harness minimal-based agent preset: Windows-friendly pwsh/bash shell, first-request anchored bootstrap, and a curated set of everyday tools.
Omnipotent agent preset for DeepSeek Harness: Standard/PTC/Minimal + routing modes
Paste/drop non-image files or folders into the DSH chat composer: paste inserts native @path references, drop inserts absolute paths.
Browser tab favicon reflects the DSH session state: idle / running / asking / done, recolored and animated from one base SVG in the browser (fully configurable colors + effects). · 浏览器标签页 favicon 实时反映 DSH 会话状态:待机 / 运行中 / 提问 / 完成,由单个 base.svg 在浏览器中动态上色与动画(颜色与特效完全可配置)。
DeepSeek Harness plugin: panel hotkeys for every interaction panel — Enter presses the confirm (primary) button, Esc presses the cancel button (approval, question/choice, plan review; Claude Code habits).
DeepSeek Harness multi-model routing plugin: route tasks to custom specialist agents (vision / image generation / translation / speech / subagent) with per-agent providers & models, multimodal account sign-in, OAuth account pools, and realtime usage stats
图书《Manim,让数学看得见》配套开源仓库:60+ 教学动画案例源码 + manim-teaching AI Skill(含 DeepSeek Harness 插件)
Real-time session cost readout for DeepSeek Harness: composer-dock cost preview, today usage chart, prices kept in sync with the DeepSeek official site (peak/off-peak aware), plus price_estimate/session_cost agent tools.
Upload an image as a full-window frosted-glass theme for DeepSeek Harness Web. Official Light / Dark / System stay in charge.
A DeepSeek Harness Mix plugin for vision routing plus GPT Image generation and editing.
DeepSeek Harness adapter that exposes each configured vision model as a selectable DeepSeek composite in Web UI.
Prism: a glassmorphism theme layer for the Web surface — adjustable blur, frost, six per-zone glass opacities, damped knobs, font scale/family, accent and backdrop hue, animated aurora or photo/GIF wallpaper
把中文场景描述转成 Anima/Anima Base 的英文自然语言 prompt:7 槽位、11 条 P 规则、负面三层、互斥自检;正负面分开输出直接复制,不输出 Params