Sorwcyra/ds-vision-skill

Near-native image understanding for DeepSeek Harness

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.

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

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). | 全网最强 DeepSeek Harness 外挂视觉插件，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）。

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

give non-vision models the ability to see images by routing images to a vision capable model

CLIProxyAPI v7 plugin for DeepSeek Responses vision preprocessing

Visual Causal Flow

Serverless Modal + FastAPI + React + ColPali + Qdrant + GPT4o Vision RAG (V-RAG) Demo