一个基于DeepSeek-Harness的ComfyUI插件

[dsh]为纯文本模型设计更强大的视觉工具箱：一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

把本机 Wallpaper Engine 的壁纸搬进 DSH 网页界面：场景壁纸由内置 MIT 开源引擎 WebWallGL 实时 WebGL 渲染（粒子 / puppet 骨骼 / SceneScript / 音频反应 / 鼠标交互），失败自动降级内嵌 MP4 与场景静态帧；Web 壁纸严格沙箱 + WE API；iOS 风格液态玻璃 UI 高度自定义，遮挡暂停省电、ffmpeg 帧率上限转码、系统音频频谱与 Now Playing、自定义上传与自动轮播；设置存宿主端，对 agent 零 token 开销。Windows / macOS / Linux 三平台原生（同一个包、同一条命令）。

AI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.

🎬AI-Powered Director: MiniMax-H3 Video Generation Plugin Directed by DeepSeek-Harness. 🤖More than Prompting. 🪄Canvas UI.

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

DSH (DeepSeek Harness) Web GUI AI image generation plugin: text-to-image & image-to-image via OpenAI-compatible endpoints (gpt-image-2), with shared cross-device history.

Full-duplex voice plugin for DeepSeek Harness: local zipformer2 streaming ASR (no API key) → editable draft; Edge TTS or local VITS / Kokoro read-aloud with live captions; true barge-in; hardened HTTP surface + model SHA256 pinning; compatible with all ds

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Precision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perfect Build Mode control, AI image generation, and fully editable PPTX. 面向专业演示设计场景，帮助用户从需求分析、视觉方向选择到原生可编辑 PPTX 交付，打造高质量、可持续修改的演示文稿。