Communitygithub.com

Video UGC Talking-Head

Convierte un still de personaje bloqueado en un video UGC 9:16 con Seedance 2.5 vía treg: duración, voz de referencia y subtítulos quemados.

¿Qué es Video UGC Talking-Head?

Skill del flujo UGC viral de Jason Zhou: tras portrait-clone, calibra el guion, toma voz de referencia, escribe el prompt Seedance 2.5, genera con treg y quema subtítulos con ffmpeg/PIL. Para agentes que entregan, no que charlan.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/superdesigndev/treg/tree/main/.agents/skills/ugc-talking-head-video
Ver original→Ver todas las habilidades

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

Documentación

¿Qué hace Video UGC Talking-Head?

Convierte una imagen de personaje fija (de portrait-clone) en un video de estilo UGC 9:16 de un personaje hablando: selecciona un clip de referencia de voz, ajusta el guion a la duración, escribe el prompt de Seedance 2.5, genera mediante treg (reAPI o PiAPI), luego agrega un encabezado emoji estático y subtítulos de frases con código. Úsalo después de portrait-clone cuando el usuario quiera que el personaje hable un guion frente a cámara.

Individual skills in this repo

This repo contains 1 individual skill — each has its own dedicated page.

portrait-clone

Turn any n reference images (with at least one person) into one exhaustively locked, always de-slopped, JSON-only AIGC image prompt whose every variable is pinned so each generation is nearly identical. Use for replicating a person's look, extracting portrait features into a prompt, locking a character, or revising such a JSON after comparing a generated image to the reference.

Skills relacionados

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

affaan-m/ECC

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...

community

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

community