使い方
- インストールコマンドをコピーし、自分の環境へ導入する前にソースを確認します。
- 必要なツール、認証情報、対応環境を原文で確認します。
- 入力と成果物を指定し、出力を資料と照合します。
npx skills add https://github.com/mckruz/comfyui-expert --skill project-manager開始前の確認
- 導入にはモデル契約、API枠、ファイルへのアクセス許可は含まれません。
- スター数や導入数は活動の指標であり、独立した品質・安全性試験ではありません。
リポジトリの原文
見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。
Project Manager
Manages the lifecycle of video production projects. Each project gets a manifest, character profiles, workflow records, and asset tracking.
Project Structure
projects/{project-name}/
manifest.yaml # Project metadata, settings, status
characters/
{name}/
profile.yaml # Character description, reference images, voice profile
references/ # Source images for this character
outputs/ # Generated outputs
workflows/ # Saved ComfyUI workflow JSONs
assets/ # External assets (audio, video, images)
notes.md # Production notes, what worked/didn'tCommands
Create New Project
When user wants to start a new project:
- Ask for project name and brief description
- Create directory structure under
projects/ - Generate
manifest.yaml:
yaml
name: "{project-name}"
description: "{description}"
created: "{ISO date}"
updated: "{ISO date}"
status: active # active | paused | completed | archived
hardware:
gpu: "RTX 5090"
vram: 32
defaults:
checkpoint: "" # Filled after first successful generation
upscaler: ""
cfg: null
sampler: ""
scheduler: ""
characters: [] # List of character names
workflows: [] # List of saved workflow files
notes: ""Create Character Profile
When user describes a character:
- Create
projects/{project}/characters/{name}/profile.yaml:
yaml
name: "{character-name}"
trigger_word: "{unique_trigger}" # e.g., "sage_character"
created: "{ISO date}"
appearance:
gender: ""
age_range: ""
ethnicity: ""
hair: ""
eyes: ""
skin: ""
build: ""
distinguishing_features: []
personality:
traits: []
voice_description: ""
reference_images:
source_type: "" # 3d_render | photograph | illustration | generated
count: 0
path: "references/"
lora:
trained: false
model_file: ""
trigger_word: ""
best_strength: null
voice:
cloned: false
model: "" # chatterbox | f5-tts | elevenlabs | rvc
sample_file: ""
settings: {}
generation_history:
preferred_method: "" # instantid | pulid | infiniteyou | kontext | lora
best_settings:
cfg: null
steps: null
sampler: ""
ip_adapter_weight: null
instantid_weight: null
successful_prompts: []
failed_approaches: []Update Project State
After any successful generation or pipeline run:
- Read current manifest
- Update
defaultswith settings that worked - Update character's
generation_history - Add workflow file to
workflows/list - Update
updatedtimestamp
List Projects
List all projects under projects/ with status and character count.
Archive Project
Set status to archived, optionally compress outputs.
Integration
- comfyui-inventory: Check what's available before recommending approaches
- comfyui-character-gen: Feed character profile as context for generation
- comfyui-voice-pipeline: Feed voice profile for synthesis
- comfyui-lora-training: Use reference images and profile for dataset prep
