ZhaoJun233/dsh-imagegen
ZhaoJun233★ 0JavaScript最后同步: 2026-08-15
Provider-neutral image generation plugin for DeepSeek Harness with Gemini and OpenAI Images compatible APIs.
README 摘要
dsh-imagegen English 简体中文 Provider-neutral image generation plugin for DeepSeek Harness. It registers the image generate agent tool and supports: - Gemini-compatible generateContent endpoints - image2 / OpenAI-compatible /images/generations endpoints - base64 and downloadable URL responses - runtime configuration from the DSH plugin settings page - secret redaction for API credentials - workspace-confined output paths and image-size limits Install Install directly from GitHub into the DSH Web profile: For local development, link the checkout instead: Restart the DSH Web host after installing or updating plugin code. Configure Open Settings → Plugins → Plugin configuration → Image generation and set: - protocol: auto , gemini , or image2 - API URL - API Key or environment-variable name - credential header and optional prefix - default model - default image2 quality - workspace-relative output directory The API Key field is write-only. Secret-role values are removed from settings responses and are never echoed by the page. The public defaults use placeholder connection values. Configure a real endpoint and credential before calling the tool. Gemini-compatible example When a base URL …
在 GitHub 查看完整 README →分类
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
★ 2,047
Anionex/agent-vision-toolkit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
★ 920
Anionex/dsh-vision-toolkit让纯文本模型更好地做视觉任务的DeepSeek Harness插件:带意图的图片问答、长截图 OCR、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.
★ 457