Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
96 plugins encontrados
dsh-cosplay-studio
wang-shuanglin/dsh-cosplay-studio
Local ComfyUI cosplay photo sets for Windows with an NVIDIA GPU (8 GB+ VRAM): deploys the ComfyUI Windows portable build and Z-Image-Turbo (8-10 GB of models) with a self-test, then turns a character name, a reference image, or a hot-character pick into a live-action cosplay photo set with base-image and shot-script approval gates.
dsh-super-image
byton-patrica/dsh-super-image
Generates images in parallel with two configurable OpenAI Images-compatible or ComfyUI backends, compares the candidates, and optionally fuses them. Visual comparison needs a vision-capable model in DSH; without one the candidates are listed unscored.
dsh-comfyui-studio
xingyeai23/dsh-comfyui-studio
ComfyUI studio in a DSH sidebar panel: connects to a local or LAN ComfyUI server, picks saved image workflows, cleans and rewrites prompts, edits LoRAs and nodes, generates images, and previews results with copyable seeds.
media-suite
do-nothing/media-suite
Familia de plugins multimedia: instala de una vez las funciones multimedia de Qwen y RunningHub e incluye ajustes globales entre proveedores.
media-suite (media-runninghub)
do-nothing/media-suite
Ejecuta flujos ComfyUI en la nube de RunningHub como un pool de tareas en segundo plano: envía un lote y un vigilante lo distribuye dentro del límite de concurrencia, consulta cada trabajo y descarga todos los resultados al disco. Al vaciarse el pool, reactiva la sesión. Un registro compartido guarda lotes, costes, niveles de instancia, horas de envío y finalización y rutas de guardado por archivo; hay un panel en vivo en la barra lateral derecha.
media-suite (media-qwen)
do-nothing/media-suite
Herramientas multimedia Qwen mediante Alibaba Cloud DashScope: comprensión multimodal de vídeo y audio, texto a voz con voces predefinidas y generación de audio para escenas.
dsh-shengtu
xuhairui-dzz/dsh-shengtu
Generación de imágenes con varios motores dentro de la conversación: herramienta de agente y panel acoplado al compositor con interruptor, presets Volcengine Ark, SiliconFlow, compatible con OpenAI o personalizado, y seguimiento local del gasto. Debes aportar la clave API del motor elegido.
dsh-deck-studio (deck-studio)
yuna78/dsh-deck-studio
Espacio de trabajo de mazos de imágenes para DSH basado en chat: convierte la intención en un guion de storyboard, genera prompts e imágenes de IA por página con revisiones individuales, ofrece nueve estilos de diseño y exporta a PDF/PPTX (una imagen de página completa por diapositiva).
dsh-image2-plugin
544244857/dsh-image2-plugin
Registra `image2_generate`, que usa tu propio relé de imágenes compatible con OpenAI para crear o editar imágenes. Generación de texto a imagen mediante POST /images/generations; edición con referencia PNG/JPEG/WebP local mediante POST /images/edits; acepta b64_json o URL de imagen. Guarda en el directorio de trabajo de la sesión y muestra el resultado en la conversación mediante su dependencia `@wisdoverse/dsh-inline-media-viewer`.
dsh-grok-byapi
ningyuanlee/dsh-grok-byapi
Proveedor de modelos Grok mediante un gateway compatible con OpenAI, con descubrimiento de modelos, generación de imagen y vídeo, herramientas de texto a voz y tareas multimedia locales persistentes.
dsh-image-bridge
kkj-luna/dsh-image-bridge
Añade generación de imagen desde texto e imagen a modelos que no dibujan. Admite cualquier API de imágenes compatible con OpenAI, varios proveedores y un modelo alternativo automático.
dsh-plugin-agnes-image
zhp282515-wq/dsh-plugin-agnes-image
Añade la herramienta agnes_image para modelos Agnes Image Flash (2.5, 2.1 y 2.0), con generación texto a imagen, imagen a imagen y composición de varias imágenes. Settings permite elegir modelo activo, tamaño y relación de aspecto predeterminados, carpeta de salida, API key e historial.
dsh-tool-comfyui
yuehancn/dsh-tool-comfyui
Genera imágenes desde el chat mediante un conjunto de workers ComfyUI locales o en LAN, con plantillas de workflow, comprobación de estado y control de cola.
dsh-media-gen
emberwingaviation/dsh-media-gen
Plugin integrado de generación de imágenes y videos para DSH: catálogo multi proveedor (gateway images/chat compatible con OpenAI, DashScope 通义万相, Seedance de Volcengine, Google Veo y tareas asíncronas /v1/videos estilo Sora con input_reference para imagen a video). Incluye image_generate / generate_video / animate_image, vista integrada en el chat, galerías y ajustes unificados. Fusiona forks de dsh-image-generation y dsh-video-gen.
dsh-imagegen-skill
dingchenhui0618-arch/dsh-imagegen-skill
Registra la skill imagegen en el registro de skills, sin copiar archivos manualmente a `$DSH_HOME/skills`. El agente usa el CLI incluido `image_gen.py` con cualquier endpoint GPT Image compatible con OpenAI para generar desde texto, editar imágenes de referencia y crear recortes con fondo transparente.
dsh-imgdraw
ninjasln-labs/dsh-imgdraw
Texto a imagen para DeepSeek Harness: herramienta de modelo `draw_image`, botón 生图 en la barra de entrada con ventana de prompt (generación asíncrona, resultados en cuadrícula de 4 y opciones de descargar/conservar/eliminar), ruta de imagen `/imgdraw` e historial persistente. Backend: DashScope wan2.7-image.
dsh-tool-imagegen
pappet/dsh-tool-imagegen
Generación texto a imagen e imagen a imagen mediante la Image API unificada de OpenRouter, con alias de modelos configurables y parámetros limitados según las capacidades del modelo en vivo, entradas de imágenes de referencia, tarjeta de ajustes y resultados en línea en el chat.
oh-my-dsh
llmpolska/oh-my-dsh
Enrutamiento de modelos por niveles para DeepSeek Harness: niveles think/build, delegación a visión (el modelo de visión solo describe imágenes; el modelo de trabajo actúa), generación de imágenes y una protección de alto impacto.
beav-deepseek-harness
jamailar/beav-deepseek-harness
Conecta DSH con Beav local para operaciones de IA en Xiaohongshu (RED/RedNote) y redes sociales: flujos de investigación de temas, conocimiento, copywriting, imagen, audio y vídeo corto con aprobación y seguimiento de artefactos.
dsh-drawcraft
vhow123/dsh-drawcraft
Drawcraft — an image-generation studio in the sidebar panel list, split into three pages that share one result. Prompt page: pick a target dialect, a style and an aspect, write one rough sentence, and a chat model returns an 11-field shot breakdown that the plugin stitches into the syntax that dialect actually accepts — six dialects (natural English, natural Chinese, GPT-Image, Midjourney, Stable Diffusion, nano-banana), 18 style presets, negative prompts, filler-word stripping and local history; an image can also be reverse-engineered into the same fields, and a one-line edit such as light turns to dusk rewrites only the named fields. Image page: text-to-image and image-to-image through a locally installed image-generation plugin or through an OpenAI-compatible endpoint you add in the panel, whose key stays on disk and is never echoed back to the browser; with a subject image attached it posts to /images/edits and carries up to four extra references. Canvas page: an infinite canvas where image, prompt and result nodes are dragged, resized, wired by hand or by generation, with undo and redo, marquee selection, copy and paste, a minimap, pointer-centred wheel zoom and JSON export and import; rendering from a node walks the whole upstream chain so no reference is dropped, one node can be pinned as the subject, and the reference library opens inside the canvas. A reference library of 4,345 Chinese-labelled entries — 1,439 poses with matching depth maps, 1,407 outfits, 1,499 portraits — is searched and faceted by pose system, angle, category, season, hair length and hairstyle, paged 24 at a time, and the entries you pick are injected into the prompt as binding constraints. Renders can pick the image channel and model, one of eight aspect sizes or follow-the-aspect, and quality at 1K/2K/4K; a preview opens into a lightbox with pointer-centred wheel zoom from 20% to 800%, drag-to-pan, double-click reset and one-click save. The prompt tools and the library are also exposed as the optimize_image_prompt, patch_image_prompt and search_reference_gallery agent tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-image-gen
adithyanraj03/dsh-image-gen
Multi-provider image generation and editing for DeepSeek Harness (OpenAI-compatible relays with custom /v1/images/generations endpoints, Gemini, Seedream, DashScope, Grok, GLM, local ComfyUI, subscription accounts), an Excalidraw MIT infinite-canvas studio with click-to-place and selection-to-edit references, and a pro viewer with zoom/pan/pinch, region notes and a markup mode that bakes marks into the pixels and sends normalized coordinates to the model.
dsh-api-free-image
apfsds-dog/dsh-api-free-image
A DSH plugin that provides API-free image generation capabilities. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-imagegen-panel
gpta76/dsh-imagegen-panel
Image-generation sidebar panel for DeepSeek Harness: works with any OpenAI-compatible image endpoint, supports reference-image edits, and ships presets for character sheets, turnarounds and expressions.
dsh-prompt-forge
vhow123/dsh-prompt-forge
Image-generation prompt workshop in the sidebar panel list, working in four directions that share one result. Idea to prompt: pick a target dialect, a style and an aspect, write one rough sentence, and a chat model returns an 11-field shot breakdown that the plugin stitches into the syntax that dialect actually accepts — six dialects (natural English, natural Chinese, GPT-Image, Midjourney, Stable Diffusion, nano-banana), 18 style presets, negative prompts, filler-word stripping and local history. Image to prompt: drop a reference image and a vision model reverse-engineers the same fields. Prompt to prompt: type one line such as light turns to dusk and only the named fields are rewritten, everything else is copied verbatim. Prompt to image: the result card, or the panel itself before any optimization has run, renders through a locally installed image-generation plugin or through an OpenAI-compatible endpoint you add in the panel, whose key stays on disk and is never echoed back to the browser; with a main image attached it posts to /images/edits and carries up to four extra references, with only text it posts to /images/generations. A reference library of 4,345 Chinese-labelled entries — 1,439 poses with matching depth maps, 1,407 outfits, 1,499 portraits — is searched and faceted by pose system, angle, category, season, hair length and hairstyle, paged 24 at a time, and the entries you pick are injected into the prompt as binding constraints. Renders can pick the image channel and model, one of eight aspect sizes or follow-the-aspect, and quality at 1K/2K/4K; a preview opens into a lightbox with pointer-centred wheel zoom from 20% to 800%, drag-to-pan, double-click reset and one-click save. The first two directions and the library are also exposed as the optimize_image_prompt, patch_image_prompt and search_reference_gallery agent tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.