# ============================================================================
# ComfyUI Model Configuration
# ============================================================================
#
# This configuration file defines all available ComfyUI models for download.
# Models are organized by category: image, video, audio, and support models.
#
# Each model entry contains:
#   - repo_id: HuggingFace repository identifier
#   - description: Human-readable description
#   - size_gb: Approximate size in gigabytes
#   - essential: Whether this is an essential model (true/false)
#   - category: Model category (image/video/audio/support)
#
# ============================================================================

# Global settings
settings:
  cache_dir: /workspace/huggingface_cache
  parallel_downloads: 1
  retry_attempts: 3
  timeout_seconds: 3600

# Model categories
model_categories:
  # ==========================================================================
  # IMAGE GENERATION MODELS
  # ==========================================================================
  image_models:
    - repo_id: black-forest-labs/FLUX.1-schnell
      description: FLUX.1 Schnell - Fast 4-step inference
      size_gb: 23
      essential: true
      category: image
      format: fp16
      vram_gb: 23
      notes: Industry-leading image generation quality

    - repo_id: black-forest-labs/FLUX.1-dev
      description: FLUX.1 Dev - Balanced quality/speed
      size_gb: 23
      essential: false
      category: image
      format: fp16
      vram_gb: 23
      notes: Development version with enhanced features

    - repo_id: stabilityai/stable-diffusion-xl-base-1.0
      description: SDXL Base 1.0 - Industry standard
      size_gb: 7
      essential: true
      category: image
      format: fp16
      vram_gb: 12
      notes: Most widely used Stable Diffusion model

    - repo_id: stabilityai/stable-diffusion-xl-refiner-1.0
      description: SDXL Refiner 1.0 - Enhances base output
      size_gb: 6
      essential: false
      category: image
      format: fp16
      vram_gb: 12
      notes: Use after SDXL base for improved details

    - repo_id: stabilityai/stable-diffusion-3.5-large
      description: SD 3.5 Large - Latest Stability AI
      size_gb: 18
      essential: false
      category: image
      format: fp16
      vram_gb: 20
      notes: Newest generation Stable Diffusion

  # ==========================================================================
  # VIDEO GENERATION MODELS
  # ==========================================================================
  video_models:
    - repo_id: THUDM/CogVideoX-5b
      description: CogVideoX-5B - Professional text-to-video
      size_gb: 20
      essential: true
      category: video
      format: fp16
      vram_gb: 20
      frames: 49
      resolution: 720p
      notes: State-of-the-art text-to-video generation

    - repo_id: stabilityai/stable-video-diffusion-img2vid
      description: SVD - 14 frame image-to-video
      size_gb: 8
      essential: true
      category: video
      format: fp16
      vram_gb: 20
      frames: 14
      resolution: 576x1024
      notes: Convert images to short video clips

    - repo_id: stabilityai/stable-video-diffusion-img2vid-xt
      description: SVD-XT - 25 frame image-to-video
      size_gb: 8
      essential: false
      category: video
      format: fp16
      vram_gb: 20
      frames: 25
      resolution: 576x1024
      notes: Extended frame count version

  # ==========================================================================
  # AUDIO GENERATION MODELS
  # ==========================================================================
  audio_models:
    - repo_id: facebook/musicgen-small
      description: MusicGen Small - Fast generation
      size_gb: 3
      essential: false
      category: audio
      format: fp32
      vram_gb: 4
      duration_seconds: 30
      notes: Fastest music generation, lower quality

    - repo_id: facebook/musicgen-medium
      description: MusicGen Medium - Balanced quality
      size_gb: 11
      essential: true
      category: audio
      format: fp32
      vram_gb: 8
      duration_seconds: 30
      notes: Best balance of speed and quality

    - repo_id: facebook/musicgen-large
      description: MusicGen Large - Highest quality
      size_gb: 22
      essential: false
      category: audio
      format: fp32
      vram_gb: 16
      duration_seconds: 30
      notes: Best quality, slower generation

  # ==========================================================================
  # SUPPORT MODELS (CLIP, IP-Adapter, etc.)
  # ==========================================================================
  support_models:
    - repo_id: openai/clip-vit-large-patch14
      description: CLIP H - For SD 1.5 IP-Adapter
      size_gb: 2
      essential: true
      category: support
      format: fp32
      vram_gb: 2
      notes: Text-image understanding model

    - repo_id: laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
      description: CLIP G - For SDXL IP-Adapter
      size_gb: 7
      essential: true
      category: support
      format: fp32
      vram_gb: 4
      notes: Larger CLIP model for SDXL

    - repo_id: google/siglip-so400m-patch14-384
      description: SigLIP - For FLUX models
      size_gb: 2
      essential: true
      category: support
      format: fp32
      vram_gb: 2
      notes: Advanced image-text alignment

# ============================================================================
# STORAGE & VRAM SUMMARIES
# ============================================================================

storage_requirements:
  essential_only:
    image: 30      # FLUX Schnell + SDXL Base
    video: 28      # CogVideoX + SVD
    audio: 11      # MusicGen Medium
    support: 11    # All 3 CLIP models
    total: 80      # Total essential storage

  all_models:
    image: 54      # All image models
    video: 36      # All video models
    audio: 36      # All audio models
    support: 11    # All support models
    total: 137     # Total with optional models

vram_requirements:
  # For 24GB GPU (RTX 4090)
  simultaneous_loadable:
    - name: Image Focus - FLUX FP16
      models: [FLUX.1 Schnell]
      vram_used: 23
      remaining: 1

    - name: Image Focus - FLUX FP8 + SDXL
      models: [FLUX.1 Schnell FP8, SDXL Base]
      vram_used: 24
      remaining: 0

    - name: Video Generation
      models: [CogVideoX-5B optimized, SDXL]
      vram_used: 24
      remaining: 0

    - name: Multi-Modal
      models: [SDXL, MusicGen Medium]
      vram_used: 20
      remaining: 4

# ============================================================================
# INSTALLATION PROFILES
# ============================================================================

installation_profiles:
  minimal:
    description: Minimal setup for testing
    categories: [support_models]
    storage_gb: 11
    estimated_time: 5-10 minutes

  essential:
    description: Essential models only (~80GB)
    categories: [image_models, video_models, audio_models, support_models]
    essential_only: true
    storage_gb: 80
    estimated_time: 1-2 hours

  image_focused:
    description: All image generation models
    categories: [image_models, support_models]
    storage_gb: 65
    estimated_time: 45-90 minutes

  video_focused:
    description: All video generation models
    categories: [video_models, image_models, support_models]
    essential_only: true
    storage_gb: 69
    estimated_time: 1-2 hours

  complete:
    description: All models (including optional)
    categories: [image_models, video_models, audio_models, support_models]
    storage_gb: 137
    estimated_time: 2-4 hours

# ============================================================================
# METADATA
# ============================================================================

metadata:
  version: 1.0.0
  last_updated: 2025-11-21
  compatible_with:
    - ComfyUI >= 0.1.0
    - Python >= 3.10
    - HuggingFace Hub >= 0.20.0
  maintainer: Valknar
  repository: https://github.com/yourusername/runpod