dsh-vision-fallback

Same capability topic

Related by capability

Ranked by shared capability topic, runtime face, tools or UI contributions, and distribution mode. This is not a similarity, quality, or compatibility ranking.

• dsh-vision-adapter给 DeepSeek Harness 加视觉能力：可视化设置页选视觉厂商（Kimi/智谱/通义/OpenAI/Gemini/豆包/MiniMax/阶跃星辰）并粘贴 API Key，聊天里即可拖图识别——图片走视觉模型、文字走 DeepSeek 推理。UI & client plugins · Installable
• dsh-vision-api-localorwebDSH 插件：可接入识图模型 API（本地大模型识图工具 + 设置界面）。配置 OpenAI 兼容的识图接口（LM Studio / vLLM / Ollama 等），接口留空即不启用识图模型。UI & client plugins · Installable
• dsh-vision-assistDeepSeek Harness 视觉助手插件：给没有视觉能力的模型配一个可随时切换的多模态识别模型。输入框图片自动落盘并改写为文本提示，主模型调用 vision_recognize 工具即可完成看图；识别模型在插件设置卡片里热更新切换。UI & client plugins · Installable
• dsh-vision-helperPersistent vision plugin for DeepSeek Harness: registers the vision_analyze tool backed by a configurable multimodal model, with a settings-page UI. Zero dependencies.UI & client plugins · Installable
• dsh-vision-imagenDeepSeek Harness 全能插件：识别/生图/改图一体化，无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型（gemini_vision / gemini_generate_image / gemini_optimize_image）。多后端：Gemini 原生 + 任意 OpenAI 兼容服务（GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转等），生成后自动视觉自检反馈，优于 modlens。UI & client plugins · Installable
• dsh-vision-linkLightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.UI & client plugins · Installable