Plugins

Puente de visión para modelos de solo texto: pega una imagen y obtén evidencia JSON estructurada (OCR, diseño, semántica).

Visión gratuita para agentes de solo texto: cadena de visión integrada sin clave más herramientas de píxeles (preguntas y respuestas, grounding, recorte, diff de píxeles, colores, OCR, trazado SVG, recorte de figuras, capturas de pantalla); pega una imagen para usarla.

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Comprensión de imágenes casi nativa para DeepSeek Harness

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

Cerebro DeepSeek + transcripción automática de imágenes: cada imagen adjunta se transcribe a texto vía un VLM compatible con OpenAI antes de llegar al DeepSeek de solo texto; vía rápida con clave propia (qwen3.7-flash por defecto u otro endpoint), u Ollama local sin configuración.

Dsh-visual-plugin: dale ojos a tu modelo de solo texto; reenvía las imágenes del usuario a cualquier modelo de visión compatible con OpenAI y ve los resultados en un panel derecho de la Web UI

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

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

MiniMax multimodal bridge: one `mmx_bridge` tool covers image understanding/generation, video, TTS, music, cover, web search and quota; optional `web_search`/`read_image` takeover; inline players/image previews right in the Web GUI (npm: `dsh-mmx-bridge`).

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Plugin de visión DeepEye para DeepSeek Harness (DSH): descripción de imágenes, OCR, VQA, diseño de UI y análisis del portapapeles.

Un plugin de dsh que permite a la IA invocar automáticamente VLM (modelos multimodales) para el análisis visual.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

DeepSeek Harness 视觉增强插件：将图片交给外部视觉模型分析，输出带坐标化视觉原语的纯文本证据，使不支持多模态的文本模型也能在对话中理解图片、截图与文档。

让 DeepSeek Harness 里任何纯文本模型都能读图。识图是按需调用的 tool —— 图片不进主模型上下文，不看就不花钱；附 23 处缺陷的评测集，换模型可自测。