#vision

Codex vision bridge for DeepSeek V4 Flash: give text-only DeepSeek image capability in Codex. Local proxy turns pasted images and view_image into text via free GLM-4V-Flash or any OpenAI-compatible vision API. No GPU, no Ollama.

DeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpoint

给 DeepSeek 等纯文本大模型外挂图像理解能力的本地中转服务。提供 OpenAI 兼容的 API，自动将图片请求交给视觉模型分析，再将结构化结果注入文本模型，使增强后的模型体验接近原生多模态。

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Give text-only models eyes: analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible endpoint. 给纯文本模型装上眼睛的 dsh 插件。

Eyes for text-only DeepSeek on DeepSeek Harness: model-invokable vision tool + wrapper adapters + general VLM channels (OpenAI-compatible / Gemini / local Ollama)

Give text-only DeepSeek models vision by describing images through an OpenAI-compatible vision model (DSH plugin)

Give Claude Code image understanding when its primary model cannot see images. Supports UI screenshots, photos, documents, charts, comparisons, and Windows clipboard input through Qwen.

Agent-first CLI for natural-language image-library search — caption once with Cerebras vision, search the whole index in one model call. No vector DB.

What: local LLM bakeoff harness (coding/vision/tools/agentic). For: objective model comparisons. How: ./setup.sh then ZWELL_BASE=… python bench_zwell.py --tag …

A skill that lets an AI agent see images through an external, OpenAI-compatible vision API.

Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.