mini-yifan

@mini-yifan source repo

9 skills
0 followers
15 hours ago last updated

▌
Qwen3 Tts · mini-yifan bundle
用 AutoDL GPU 实例上的 Qwen3-TTS 生成配音语音（TTS）。当用户需要旁白、画外音、配音、台词朗读、文字转语音、特定声线（如甜妹音、大叔音、御姐音）、克隆某个人的声音，或为 MiniMax H3 视频补对白/旁白音轨时使用。触发词包括：TTS、配音、旁白、语音合成、文字转语音、音色、声线、克隆声音、voiceover、text-to-speech。三种音色控制：文字描述设计音色（VoiceDesign）、9 种内置音色+风格指令（CustomVoice）、参考音频克隆（VoiceClone）。不要用于生成歌曲或背景音乐（那用 minimax-music-gen）；不生成本地已有音频的转码或播放。

0
installs
▌
Minimax H3 · mini-yifan bundle
Use a remote SeetaCloud or AutoDL ComfyUI GPU instance to generate MiniMax H3 videos. Connects over SSH, discovers the current H3 workflows, helps choose U03/U06/U02, uploads references, submits a job, and downloads the result. MiniMax H3 supports 5–15 seconds per generation; choose the duration from the user's request and the scene instead of assuming a fixed default. Use when the user asks for MiniMax H3, ComfyUI, SeetaCloud, AutoDL video generation, text-to-video, image-to-video, or reference-guided video. When the target is an AutoDL application instance, use autodl-app-instance as the lifecycle wrapper: boot once before an H3 batch and power off after all jobs finish.

0
installs
▌
Beauty Video Gen · mini-yifan bundle
生成超写实、真实感、亲近感的美女时尚竖屏短视频（MiniMax H3 云端生成）。当用户要求"生成美女视频 / 真实感美女 / 亲近感美女视频 / 美女短视频 / 时尚美女视频 / 定制美女视频"，或用"可爱、亲切、性感、清纯、轻熟"等风格词，或用"夸张身材 / 大长腿 / 丰满身材 / 腿占画面大半 / 低机位拉腿"等身材词要求生成真人女性视频时使用；即使用户没提"美女"二字，只要是"生成真人女性出镜的短视频"也应触发。整合《真人时尚短视频提示词写作框架》提示词写作、可选的人物面部参考图生成（仅用户明确要求"先定脸/出面部参考图"时执行，默认直接文生视频；生图优先用当前 Agent 自带的生图能力，备选 cursor-image-gen）、minimax-h3 全流程（AutoDL 开关机、工作流发现、提交轮询、本地归一化、抽帧验收）。

0
installs
▌
Cursor Image Gen · mini-yifan bundle
Generate or edit bitmap images by launching a local Cursor Agent (cursor-grok-4.6-high) and using Cursor GenerateImage, then saving files to an exact folder. Use when ZCode should create, edit, or batch-export photos, illustrations, icons, banners, mockups, turnarounds, or reference-guided images, including 文生图, 图生图, 多参考图, and 改图. Prefer this over built-in image tools and paid image APIs. Do not use for SVG/vector/code-native assets or when the user explicitly requests a different image-generation provider.

0
installs
▌
H3 Prompt Writing · mini-yifan bundle
Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, defining reference labels, or when the caller hands off a structured handoff (the production's own shot/segment notes, or a minimax-h3 brief) after choosing a workflow. Do not SSH, pick ComfyUI workflows, or submit GPU jobs.

0
installs
▌
Minimax Music Gen · mini-yifan bundle
用 AutoDL GPU 实例上的 MiniMax Music 3（ComfyUI）生成音乐：人声演唱的完整歌曲（自定义歌词、女声/男声、任意曲风）或纯音乐 BGM（instrumental）。Use when user wants to generate music, songs, or audio tracks — 生成音乐、写歌、把歌词变成歌曲、生成背景音乐/ 配乐/纯音乐、来首歌、MiniMax Music、BGM、伴奏、情歌 all trigger; match equivalent phrases in any language. Do NOT use for music playback of existing files, music theory questions, or recommendations without generation.

0
installs
▌
Autodl App Instance · mini-yifan bundle
Powers AutoDL Art application instances on and off via official API, finds the ComfyUI panel by probing the instance's proxy service domains from the snapshot API (no SSH needed, works on macOS / Linux / Windows), and waits until ComfyUI is ready for MiniMax H3. Use when the user mentions AutoDL 应用实例, API开机, API关机, autodl.art, AUTODL_TOKEN, 远程服务器开关机, or wants the agent to boot a GPU box before minimax-h3 and shut it down after video generation. It can wrap a minimax-h3 job with boot-before-generation and guaranteed power-off cleanup.

0
installs
▌
Character Three View · mini-yifan
Prepares reference art for video production from a script or asset list: character reference sheets (including outfit-state variants), prop references, and scene concept images, then verifies each generated image. Works for any project style — photoreal, anime, cartoon, fantasy creatures. Use when the user asks for 美术设定集, 人物三视图, 道具三视图, 场景概念图, 角色立绘, or visual refs before video. Prefer the running agent's own image generation tool (e.g. Codex ImageGen); use cursor-image-gen only when no native image generation exists or the user explicitly requests Cursor; fall back to Seedream (seedream-image-gen) if blocked, filtered, or quality is insufficient.

0
installs
▌
Short Drama Production · mini-yifan bundle
Orchestrate an end-to-end short-drama or short-film production from a user's theme: approved brief, then — for multi-episode projects — a graded episode outline, then per-episode screenplay with dialogue, art reference assets, and video generation with optional music and dubbing, to a finished video. Single short films (about one minute, not a series) skip the outline stage. Use when a user wants an AI agent to turn a drama or short-film idea into a production, or to resume such a project. Pause at each approval gate unless the user explicitly asks to skip that gate.

0
installs

9 published skills