Plugins

Crea vídeos promocionales verticales de 1080x1920 a partir de un JSON de storyboard con 7 herramientas (doctor, setup, catalog, guide, validate, render, verify), renderizados localmente con Remotion.

Controla un servidor ComfyUI local o remoto desde DeepSeek Harness: las herramientas comfyui_run / comfyui_object_info / comfyui_workflow generan y editan imágenes y vídeos, con una biblioteca de flujos de trabajo (extracción de grafos: por componente / flujo principal / todo), un área de carga con coincidencia automática de resolución, una cola en vivo, plantillas de SDXL y Wan 2.1, una habilidad complementaria y un proxy de medios del mismo origen.

Crea escenas de producto editables en Blender para DSH. Parte de recetas de altavoz, taza y lámpara, o de modelos importados; consulta los resultados guardados en Lighttable, compara revisiones y ajusta dimensiones, materiales, cámaras y luces. Coloca modelos estáticos sobre mallas reales en una operación y guarda una vista estática completa sin alterar cámaras ni animaciones existentes. Corrige coordenadas de textura repetida en caras planas personalizadas sin cambiar la geometría. Renderiza imágenes o vídeos de tomas guardadas y exporta revisiones editables con sus recursos. Inspecciones geométricas nativas, revisiones inmutables y aprobación ayudan a proteger el trabajo existente. Compatible con DSH 0.2.1-rc.1 y el host heredado; incluye 20 herramientas de modelado, revisión y entrega.

Permite que el agente explore Bilibili mediante un subagente y comunique qué merece la pena ver, con notas por vídeo, panel de tarjetas y bandeja de entrada para menciones, respuestas y vídeos compartidos.

Kit de apariencia para DeepSeek Harness. Ajusta aparte opacidad y desenfoque de vidrio esmerilado en 8 superficies (fondo, barra lateral, tarjetas/paneles, entradas/controles, ajustes, marco del chat, trayectoria, producidos/destacados — 9 con dsh-better-sidebar). Cualquier imagen o vídeo de fondo, con editor de posición (arrastrar para mover, rueda para ampliar) y 5 modos de disposición (Fit/Fill/Stretch/Tile/Center); los vídeos se repiten en bucle sin sonido, sobreviven al refresco y capturan un fotograma en vivo para vista previa, color y encuadre. Rota varias imágenes (aleatorio/orden, por refresco/día/semana). También: rueda de color estilo PS, extracción del color del fondo en un clic, 6 preajustes + perfiles guardados, cambio automático día/noche y exportación/importación del tema.

Lectura profunda y resumen para DSH: convierte libros, artículos, vídeos y webs en notas estructuradas de Obsidian mediante parsers de plugins, subagentes paralelos MapReduce de lectura profunda, salidas JSON Schema y caché idempotente.

Deja que el Pez Azul Grande y Gordo explore Bilibili: comenta por ti, te envía hallazgos interesantes por DM y mantiene un diario y memoria para resúmenes a largo plazo. Filtra videos según tus gustos, crea digestos Markdown y puede vigilar comentarios y responder. En Circle Mode solo responde en hilos que el uploader del video haya invitado explícitamente mediante un comentario de nivel superior; las solicitudes de espectadores normales no cuentan y nunca inicia un nuevo comentario de nivel superior. Comentarios, DM, ejecución automática y vigilancia están desactivados por defecto. Requiere Node 22, DSH 0.1.7-rc.1+, una cuenta de Bilibili con sesión iniciada, una ruta de modelo y Python.

Asistente de Douyin: elige vídeos a diario, lee comentarios y genera un informe con fecha. Dar Me gusta y comentar con mención @ están ambos en off por defecto. También publica clips renderizados con tu propio ComfyUI. Solo Windows; requiere Python 3 y Chrome del sistema. En el primer inicio hay que ejecutar install-main-dependencies e iniciar sesión con un código QR.

Puente MCP hacia gemini.google.com: análisis de visión de imágenes y vídeos, generación de imágenes con Imagen y vídeos con Veo, y gestión de conversaciones usando la sesión del navegador ya iniciada, sin clave de API.

Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.

Usa imágenes y vídeos locales como fondo de la ventana de escritorio DSH: rotación temporizada con fundidos cruzados de 0,7 s, espera a que esté listo el primer fotograma, tinta clara/oscura automática para legibilidad, ajuste de desenfoque y opacidad de panel/barra lateral, miniaturas de vídeo y endpoint probe con estado de carga, capas y selectores. Solo lee los archivos locales que indiques.

Da a dsh la capacidad de generar imágenes y vídeos a través de la API grok2api.

Browses Bilibili on your behalf and actually takes part: search videos, like, coin, send danmaku, post comments, reply to other people, and keep replying when someone answers back. Reads the video's Bilibili AI subtitle (or transcribes the audio locally when there is none) so its comments talk about what the video really says, and it reads that same content before choosing whom to reply to. Instead of copying other people's sentences, it distills rules about how to sound like a person and gets less AI-ish the more it runs. Skips videos it already browsed, de-duplicates replies per thread, and after too many rounds with the same person in one comment section it reviews whether the exchange has any substance -- if it looks like two bots complimenting each other, it says one last line and stops replying to that person there. Checks whether each comment is genuinely public or only visible to your own account, can scan any time window (last hour / day / 3 days / all) and lists the ones others cannot see, warning you on the overview when replies got folded. Six-tab settings panel where every change takes effect immediately with no restart, a manual run that queues behind the background listener instead of being refused, and an environment self-check that tells you exactly what to install. Requires Python 3 for the Bilibili actions; the built-in check lists any missing packages.

Runs a Douyin subagent that browses videos and reads comments in valley hours and reports back, with dy_* tools for publishing and replying (comments sent from the already-logged-in page with its own request signature, no IM ticket), a daily quota timer, and a settings panel under Settings → Douyin: master switch, auto mode, valley windows, rounds per day and report depth. Windows-oriented; needs the separate douyin-mcp binary (yunsur/douyin-mcp releases, path set via dy_config mcpExe) and an Edge/Chromium login; replying needs a logged-in browser on a CDP port; publishing needs extra credentials most accounts lack.

Bilibili curation floating panel for DSH: learns your interests on a probability schedule and decays them by half-life, picks videos inside a token budget derived from a daily money cap, and mentions you only when a fit score passes a threshold. Comments are off by default; once enabled they run in draft-and-confirm or self-checked auto mode under a daily quota, with a hard no-comment rule for political, government and frontier-science topics, and comment text is scrubbed for account identifiers before it can be posted. It signs in through your own Bilibili account cookies; a separate posting account is recommended.

Generate images and videos, edit images, remove backgrounds, upscale images, upload reference media, and check Fotor credits.

Bilibili autopilot run by a local Ollama model: it picks videos within per-topic quota, reads subtitles, hot comments and keyframes, decides whether a reply is warranted, then writes and posts one comment through a five-level safety gate. Triggered by dsh-schedule; write tools are not registered while commenting is disabled. v1.1 hardens the write path: revoking write access is a runtime state checked before every send, publishing is atomic, risk-control errors persist as a pause, and the final post re-checks persona style. Needs Python 3.10+ with the repo's requirements.txt installed.

Personal WeChat and WeCom (企业微信) bridge: QR pairing, one DSH conversation per chat, two-way text/image/video/document/archive transfer, chat commands (/help, /status, /new, /stop, /friends) answered by the bridge itself without spending a model turn, a switch that restricts the bot to 1:1 chats (group messages are dropped silently and counted), remote approval by replying 1 or 2 in the chat, and a two-way WeCom intelligent robot over its long connection (no public URL needed) that also receives and sends images, files and videos.

Reads a local video or page link with ffmpeg and Paraformer ASR, returning a timestamped transcript plus key-frame images the agent can open; finds candidate videos by keyword and installs its own runtime dependencies on first use. Requires Python 3.8+ on PATH; video_discover also needs a one-time douyin/xiaohongshu login.

DSH 生图+生视频整合插件：统一多供应商目录（OpenAI 兼容 images/chat 网关、DashScope 通义万相、火山 Seedance、Google Veo、Sora 风格 /v1/videos 异步任务含 input_reference 图生视频），提供 image_generate / generate_video / animate_image 工具，对话内联显示、图片与视频画廊、统一设置面板。Fork 合并自 dsh-image-generation 与 dsh-video-gen

Region & sticker image skin for the DSH (DeepSeek Harness) web UI - paint the window, center, sidebar, welcome, right panel and composer with your own images, GIFs or videos, add two draggable stickers, and let the interface take its colour from your wall

Turns course, lecture, tutorial, meeting, and talk videos into structured study notes: it extracts the audio track with ffmpeg, transcribes it with Whisper, then writes notes with a chapter outline, emphasis markers, and a quick-reference card.

Fondo dinámico a pantalla completa con vídeos e imágenes locales, controles de efectos en vivo, cambio de fondo e importación del workshop de Wallpaper Engine; los ajustes se guardan automáticamente.

Rotates images and videos from a media folder as the DSH UI background, with panel controls for the rotation interval and UI opacity.