valknar/runpod
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main
runpod/models_huggingface.yaml
Sebastian Krüger 2189697734
All checks were successful
Build and Push RunPod Docker Image / build-and-push (push) Successful in 14s
Details
refactor: remove type field from models_huggingface.yaml and include type in dest paths 
- Prepended ComfyUI model type folder (checkpoints/, clip/, vae/, etc.) to all dest paths
- Removed separate 'type' field from all model entries
- Consolidated SD3.5 duplicate entries (5 → 1)
- Simplified model configuration by embedding directory structure directly in destination paths

This change eliminates the need to parse the 'type' field separately in artifact_huggingface_download.sh,
making the configuration more explicit and easier to understand.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-25 19:19:42 +01:00

716 lines
25 KiB
YAML
Raw Permalink Blame History

settings:
cache_dir: /workspace/huggingface_cache
parallel_downloads: 1
retry_attempts: 3
timeout_seconds: 3600
model_categories:
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
files:
- source: flux1-schnell.safetensors
dest: unet/flux1-schnell.safetensors
- 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
files:
- source: flux1-dev.safetensors
dest: unet/flux1-dev.safetensors
- repo_id: runwayml/stable-diffusion-v1-5
description: SD 1.5 - For AnimateDiff
size_gb: 4
essential: true
category: image
format: fp16
vram_gb: 8
notes: Stable Diffusion 1.5 required for AnimateDiff motion modules
files:
- source: v1-5-pruned-emaonly.safetensors
dest: checkpoints/v1-5-pruned-emaonly.safetensors
- 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
files:
- source: sd_xl_base_1.0.safetensors
dest: checkpoints/sd_xl_base_1.0.safetensors
- 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
files:
- source: sd_xl_refiner_1.0.safetensors
dest: checkpoints/sd_xl_refiner_1.0.safetensors
- repo_id: stabilityai/stable-diffusion-3.5-large
description: SD 3.5 Large Complete - Checkpoint and text encoders
size_gb: 31
essential: false
category: image
format: mixed
vram_gb: 20
notes: Complete SD3.5 Large model with checkpoint and all text encoders (CLIP-L,
CLIP-G, T5-XXL)
files:
- source: sd3.5_large.safetensors
dest: checkpoints/sd3.5_large.safetensors
- source: text_encoders/clip_l.safetensors
dest: checkpoints/clip_l.safetensors
- source: text_encoders/clip_g.safetensors
dest: checkpoints/clip_g.safetensors
- source: text_encoders/t5xxl_fp16.safetensors
dest: checkpoints/t5xxl_fp16.safetensors
- repo_id: John6666/diving-illustrious-real-asian-v50-sdxl
description: Diving Illustrious Real Asian v5.0 - Photorealistic Asian subjects
size_gb: 7
essential: false
category: image
format: fp16
vram_gb: 12
notes: SDXL fine-tune specializing in photorealistic Asian subjects with illustrious
quality
files:
- source: unet/diffusion_pytorch_model.safetensors
dest: checkpoints/diving-illustrious-real-asian-v50-sdxl.safetensors
- repo_id: playgroundai/playground-v2.5-1024px-aesthetic
description: Playground v2.5 - 1024px aesthetic images
size_gb: 7
essential: false
category: image
format: fp16
vram_gb: 12
notes: Highly aesthetic 1024x1024 outputs, outperforms SDXL and DALL-E 3 in user
studies
files:
- source: playground-v2.5-1024px-aesthetic.fp16.safetensors
dest: checkpoints/playground-v2.5-1024px-aesthetic.safetensors
- repo_id: Lykon/dreamshaper-8
description: DreamShaper 8 - Multi-style versatile model
size_gb: 4
essential: false
category: image
format: fp16
vram_gb: 8
notes: Versatile SD1.5 fine-tune balancing photorealistic and anime styles with
strong LoRA support
files:
- source: unet/diffusion_pytorch_model.fp16.safetensors
dest: checkpoints/dreamshaper-8.safetensors
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, auto-downloaded by DownloadAndLoadCogVideoModel
node
files:
- source: transformer/diffusion_pytorch_model-00001-of-00002.safetensors
dest: diffusion_models/cogvideox-5b-transformer-00001-of-00002.safetensors
- source: transformer/diffusion_pytorch_model-00002-of-00002.safetensors
dest: diffusion_models/cogvideox-5b-transformer-00002-of-00002.safetensors
- source: transformer/diffusion_pytorch_model.safetensors.index.json
dest: diffusion_models/cogvideox-5b-transformer.safetensors.index.json
- repo_id: THUDM/CogVideoX-5b-I2V
description: CogVideoX-5B-I2V - Image-to-video generation
size_gb: 20
essential: true
category: video
format: fp16
vram_gb: 20
frames: 49
resolution: 720p
notes: Image-to-video model, auto-downloaded by DownloadAndLoadCogVideoModel node
files:
- source: transformer/diffusion_pytorch_model-00001-of-00003.safetensors
dest: diffusion_models/cogvideox-5b-i2v-transformer-00001-of-00003.safetensors
- source: transformer/diffusion_pytorch_model-00002-of-00003.safetensors
dest: diffusion_models/cogvideox-5b-i2v-transformer-00002-of-00003.safetensors
- source: transformer/diffusion_pytorch_model-00003-of-00003.safetensors
dest: diffusion_models/cogvideox-5b-i2v-transformer-00003-of-00003.safetensors
- source: transformer/diffusion_pytorch_model.safetensors.index.json
dest: diffusion_models/cogvideox-5b-i2v-transformer.safetensors.index.json
- 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
files:
- source: svd.safetensors
dest: checkpoints/svd.safetensors
- 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
files:
- source: svd_xt.safetensors
dest: checkpoints/svd_xt.safetensors
- repo_id: Comfy-Org/HunyuanVideo_repackaged
description: HunyuanVideo Complete - 720p T2V/I2V models with VAE and encoders
size_gb: 51
essential: true
category: video
format: bf16
vram_gb: 24
frames: 129
resolution: 720p
notes: Complete HunyuanVideo family - T2V, I2V v1/v2, 3D VAE, LLaVA LLaMA3 text/vision
encoders
files:
- source: split_files/diffusion_models/hunyuan_video_t2v_720p_bf16.safetensors
dest: diffusion_models/hunyuan_video_t2v_720p_bf16.safetensors
- source: split_files/diffusion_models/hunyuan_video_image_to_video_720p_bf16.safetensors
dest: diffusion_models/hunyuan_video_image_to_video_720p_bf16.safetensors
- source: split_files/diffusion_models/hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors
dest: diffusion_models/hunyuan_video_v2_replace_image_to_video_720p_bf16.safetensors
- source: split_files/vae/hunyuan_video_vae_bf16.safetensors
dest: diffusion_models/hunyuan_video_vae_bf16.safetensors
- source: split_files/text_encoders/llava_llama3_fp8_scaled.safetensors
dest: diffusion_models/llava_llama3_fp8_scaled.safetensors
- source: split_files/clip_vision/llava_llama3_vision.safetensors
dest: diffusion_models/llava_llama3_vision.safetensors
- repo_id: Comfy-Org/HunyuanVideo_1.5_repackaged
description: HunyuanVideo 1.5 Complete - 720p/1080p T2V/SR with encoders
size_gb: 51.5
essential: true
category: video
format: fp16
vram_gb: 24
frames: 129-257
resolution: 720p-1080p
notes: Complete HunyuanVideo 1.5 - T2V 720p, SR 1080p, VAE, Qwen 2.5 VL, ByT5
GlyphXL encoders
files:
- source: hunyuanvideo1.5_720p_t2v_fp16.safetensors
dest: diffusion_models/hunyuanvideo1.5_720p_t2v_fp16.safetensors
- source: hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors
dest: diffusion_models/hunyuanvideo1.5_1080p_sr_distilled_fp16.safetensors
- source: hunyuanvideo15_vae_fp16.safetensors
dest: diffusion_models/hunyuanvideo15_vae_fp16.safetensors
- source: qwen_2.5_vl_7b_fp8_scaled.safetensors
dest: diffusion_models/qwen_2.5_vl_7b_fp8_scaled.safetensors
- source: byt5_small_glyphxl_fp16.safetensors
dest: diffusion_models/byt5_small_glyphxl_fp16.safetensors
- repo_id: Comfy-Org/Wan_2.2_ComfyUI_Repackaged
description: Wan2.2 Complete - All video models, VAEs, and LoRAs
size_gb: 220
essential: true
category: video
format: mixed
vram_gb: 24
frames: 81
resolution: 640x640
notes: Complete Wan2.2 model family - TI2V 5B, T2V 14B, I2V 14B, Animate, S2V,
Fun Inpaint/Control/Camera, VAEs, CLIP Vision H, Wav2Vec2, and LoRA accelerators
files:
- source: wan2.2_ti2v_5B_fp16.safetensors
dest: diffusion_models/wan2.2_ti2v_5B_fp16.safetensors
- source: wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors
- source: wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors
- source: wan2.2_i2v_high_noise_14B_fp16.safetensors
dest: diffusion_models/wan2.2_i2v_high_noise_14B_fp16.safetensors
- source: wan2.2_i2v_low_noise_14B_fp16.safetensors
dest: diffusion_models/wan2.2_i2v_low_noise_14B_fp16.safetensors
- source: wan2.2_animate_14B_bf16.safetensors
dest: diffusion_models/wan2.2_animate_14B_bf16.safetensors
- source: wan2.2_s2v_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_s2v_14B_fp8_scaled.safetensors
- source: wan2.2_s2v_14B_bf16.safetensors
dest: diffusion_models/wan2.2_s2v_14B_bf16.safetensors
- source: wan2.2_fun_inpaint_high_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_fun_inpaint_high_noise_14B_fp8_scaled.safetensors
- source: wan2.2_fun_inpaint_low_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_fun_inpaint_low_noise_14B_fp8_scaled.safetensors
- source: wan2.2_fun_control_high_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_fun_control_high_noise_14B_fp8_scaled.safetensors
- source: wan2.2_fun_control_low_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_fun_control_low_noise_14B_fp8_scaled.safetensors
- source: wan2.2_fun_camera_high_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_fun_camera_high_noise_14B_fp8_scaled.safetensors
- source: wan2.2_fun_camera_low_noise_14B_fp8_scaled.safetensors
dest: diffusion_models/wan2.2_fun_camera_low_noise_14B_fp8_scaled.safetensors
- source: wan2.2_vae.safetensors
dest: diffusion_models/wan2.2_vae.safetensors
- source: wan_2.1_vae.safetensors
dest: diffusion_models/wan_2.1_vae.safetensors
- source: clip_vision_h.safetensors
dest: diffusion_models/clip_vision_h.safetensors
- source: wav2vec2_large_english_fp16.safetensors
dest: diffusion_models/wav2vec2_large_english_fp16.safetensors
- source: lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
dest: diffusion_models/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors
- source: wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors
dest: diffusion_models/wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors
- source: wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors
dest: diffusion_models/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors
- source: wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors
dest: diffusion_models/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors
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
files:
- source: pytorch_model.bin
dest: musicgen/musicgen-small-pytorch_model.bin
- 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
files:
- source: pytorch_model.bin
dest: musicgen/musicgen-medium-pytorch_model.bin
- 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
files:
- source: pytorch_model-00001-of-00002.bin
dest: musicgen/musicgen-large-pytorch_model-00001-of-00002.bin
- source: pytorch_model-00002-of-00002.bin
dest: musicgen/musicgen-large-pytorch_model-00002-of-00002.bin
- source: pytorch_model.bin.index.json
dest: musicgen/musicgen-large-pytorch_model.bin.index.json
- repo_id: Comfy-Org/ACE-Step_ComfyUI_repackaged
description: ACE Step v1 3.5B - Fast coherent music generation with 19-language
support
size_gb: 7.7
essential: true
category: audio
format: safetensors
vram_gb: 16
duration_seconds: 240
notes: 15x faster than LLM baselines, superior structural coherence, voice cloning,
19-language lyrics
files:
- source: all_in_one/ace_step_v1_3.5b.safetensors
dest: checkpoints/ace_step_v1_3.5b.safetensors
- repo_id: ACE-Step/ACE-Step-v1-chinese-rap-LoRA
description: ACE Step Chinese RAP LoRA - Enhanced Chinese pronunciation and hip-hop
genre
size_gb: 0.3
essential: false
category: audio
format: safetensors
notes: Improves Chinese pronunciation accuracy and hip-hop/electronic genre adherence
files:
- source: pytorch_lora_weights.safetensors
dest: loras/ace-step-chinese-rap-lora.safetensors
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 for IP-Adapter
files:
- source: model.safetensors
dest: clip_vision/CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors
- 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 IP-Adapter
files:
- source: open_clip_model.safetensors
dest: clip_vision/CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors
- 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
files:
- source: model.safetensors
dest: clip_vision/siglip-so400m-patch14-384.safetensors
- repo_id: black-forest-labs/FLUX.1-schnell
description: FLUX VAE - Autoencoder for FLUX models
size_gb: 0.5
essential: true
category: support
format: safetensors
vram_gb: 1
notes: VAE autoencoder required for FLUX image decoding
files:
- source: ae.safetensors
dest: vae/ae.safetensors
- repo_id: ai-forever/Real-ESRGAN
description: RealESRGAN x2 - 2x upscaling model
size_gb: 0.06
essential: true
category: support
format: pth
vram_gb: 2
notes: Fast 2x upscaling model for general purpose enhancement
files:
- source: RealESRGAN_x2.pth
dest: upscale_models/RealESRGAN_x2.pth
- repo_id: ai-forever/Real-ESRGAN
description: RealESRGAN x4 - 4x upscaling model
size_gb: 0.06
essential: true
category: support
format: pth
vram_gb: 4
notes: High-quality 4x upscaling model for detail enhancement
files:
- source: RealESRGAN_x4.pth
dest: upscale_models/RealESRGAN_x4.pth
- repo_id: Comfy-Org/Wan_2.1_ComfyUI_repackaged
description: UMT5-XXL FP8 - Text encoder for all Wan2.2 models
size_gb: 10
essential: true
category: support
format: fp8_scaled
vram_gb: 5
notes: Shared text encoder for all Wan2.2 models (5B and 14B), FP8 quantized
files:
- source: umt5_xxl_fp8_e4m3fn_scaled.safetensors
dest: text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors
animatediff_models:
- repo_id: guoyww/animatediff
description: AnimateDiff Motion Modules
size_gb: 2
essential: true
category: animatediff
filename: mm_sd_v15
format: safetensors
vram_gb: 4
notes: Motion modules for AnimateDiff text-to-video
files:
- source: mm_sd_v15_v2.ckpt
dest: animatediff_models/mm_sd_v15_v2.ckpt
controlnet_models:
- repo_id: lllyasviel/control_v11p_sd15_canny
description: ControlNet Canny - Edge detection control for SD 1.5
size_gb: 1.5
essential: false
category: controlnet
format: safetensors
vram_gb: 2
notes: Precise edge-based composition control
files:
- source: diffusion_pytorch_model.safetensors
dest: controlnet/control_v11p_sd15_canny.safetensors
- repo_id: lllyasviel/control_v11f1p_sd15_depth
description: ControlNet Depth - Depth map control for SD 1.5
size_gb: 1.5
essential: false
category: controlnet
format: safetensors
vram_gb: 2
notes: Depth-based spatial control
files:
- source: diffusion_pytorch_model.safetensors
dest: controlnet/control_v11p_sd15_depth.safetensors
- repo_id: diffusers/controlnet-canny-sdxl-1.0
description: ControlNet Canny SDXL - Edge detection for SDXL
size_gb: 2.5
essential: false
category: controlnet
format: safetensors
vram_gb: 3
notes: Canny edge control for SDXL models
files:
- source: diffusion_pytorch_model.safetensors
dest: controlnet/controlnet-canny-sdxl-1.0.safetensors
- repo_id: diffusers/controlnet-depth-sdxl-1.0
description: ControlNet Depth SDXL - Depth map for SDXL
size_gb: 2.5
essential: false
category: controlnet
format: safetensors
vram_gb: 3
notes: Depth control for SDXL models
files:
- source: diffusion_pytorch_model.safetensors
dest: controlnet/controlnet-depth-sdxl-1.0.safetensors
ipadapter_models:
- repo_id: h94/IP-Adapter
description: IP-Adapter SDXL Base - Style & Composition
size_gb: 1.3
essential: true
category: ipadapter
format: safetensors
vram_gb: 4
notes: Basic IP-Adapter for SDXL
files:
- source: sdxl_models/ip-adapter_sdxl.safetensors
dest: ipadapter/ip-adapter_sdxl.safetensors
- repo_id: h94/IP-Adapter
description: IP-Adapter SDXL VIT-H - For CLIP-ViT-H
size_gb: 0.9
essential: true
category: ipadapter
format: safetensors
vram_gb: 4
notes: IP-Adapter for SDXL with VIT-H CLIP vision model
files:
- source: sdxl_models/ip-adapter_sdxl_vit-h.safetensors
dest: ipadapter/ip-adapter_sdxl_vit-h.safetensors
- repo_id: h94/IP-Adapter
description: IP-Adapter SDXL Plus - High Strength Composition
size_gb: 0.9
essential: false
category: ipadapter
format: safetensors
vram_gb: 4
notes: Enhanced composition control with higher strength
files:
- source: sdxl_models/ip-adapter-plus_sdxl_vit-h.safetensors
dest: ipadapter/ip-adapter-plus_sdxl_vit-h.safetensors
- repo_id: h94/IP-Adapter
description: IP-Adapter SDXL Plus Face - Face-focused generation
size_gb: 0.5
essential: false
category: ipadapter
format: safetensors
vram_gb: 4
notes: Specialized for face transfer and portrait generation
files:
- source: sdxl_models/ip-adapter-plus-face_sdxl_vit-h.safetensors
dest: ipadapter/ip-adapter-plus-face_sdxl_vit-h.safetensors
diffrhythm_models:
- repo_id: ASLP-lab/DiffRhythm-1_2
description: DiffRhythm 1.2 - 95 second generation model
size_gb: 2
essential: true
category: diffrhythm
format: pt
vram_gb: 12
duration_seconds: 95
notes: Latest 95-second generation model
files:
- source: cfm_model.pt
dest: TTS/DiffRhythm/cfm_model_v1_2.pt
- repo_id: ASLP-lab/DiffRhythm-full
description: DiffRhythm Full - 4m45s full-length generation
size_gb: 2
essential: false
category: diffrhythm
format: pt
vram_gb: 16
duration_seconds: 285
notes: Full-length 4 minute 45 second music generation
files:
- source: cfm_model.pt
dest: TTS/DiffRhythm/cfm_full_model.pt
- repo_id: ASLP-lab/DiffRhythm-base
description: DiffRhythm Base - 95 second base model
size_gb: 2
essential: false
category: diffrhythm
format: pt
vram_gb: 12
duration_seconds: 95
notes: Base 95-second model
files:
- source: cfm_model.pt
dest: TTS/DiffRhythm/cfm_model.pt
- repo_id: ASLP-lab/DiffRhythm-vae
description: DiffRhythm VAE - Variational autoencoder
size_gb: 1
essential: true
category: diffrhythm
format: pt
vram_gb: 2
notes: VAE component fine-tuned from Stable Audio Open (Stability AI Community
License)
files:
- source: vae_model.pt
dest: TTS/DiffRhythm/vae_model.pt
- repo_id: OpenMuQ/MuQ-MuLan-large
description: MuQ-MuLan-large - Music-text joint embedding (~700M parameters)
size_gb: 3
essential: true
category: diffrhythm
format: bin
vram_gb: 4
notes: Music-text joint embedding for semantic understanding (English/Chinese)
files:
- source: config.json
dest: TTS/DiffRhythm/MuQ-MuLan-large/config.json
- source: pytorch_model.bin
dest: TTS/DiffRhythm/MuQ-MuLan-large/pytorch_model.bin
- repo_id: OpenMuQ/MuQ-large-msd-iter
description: MuQ-large-msd-iter - Music representation learning (~300M parameters)
size_gb: 1.2
essential: true
category: diffrhythm
format: safetensors
vram_gb: 2
notes: Music representation model trained on Million Song Dataset
files:
- source: config.json
dest: TTS/DiffRhythm/MuQ-large-msd-iter/config.json
- source: model.safetensors
dest: TTS/DiffRhythm/MuQ-large-msd-iter/model.safetensors
- repo_id: FacebookAI/xlm-roberta-base
description: XLM-RoBERTa Base - Multilingual text encoder (100 languages, 0.3B
params)
size_gb: 1.1
essential: true
category: diffrhythm
format: safetensors
vram_gb: 1
notes: Multilingual text encoding for 100 languages
files:
- source: config.json
dest: TTS/DiffRhythm/xlm-roberta-base/config.json
- source: model.safetensors
dest: TTS/DiffRhythm/xlm-roberta-base/model.safetensors
- source: sentencepiece.bpe.model
dest: TTS/DiffRhythm/xlm-roberta-base/sentencepiece.bpe.model
- source: tokenizer.json
dest: TTS/DiffRhythm/xlm-roberta-base/tokenizer.json
- source: tokenizer_config.json
dest: TTS/DiffRhythm/xlm-roberta-base/tokenizer_config.json
storage_requirements:
essential_only:
image: 30
video: 28
audio: 11
support: 11
diffrhythm: 10
total: 90
all_models:
image: 54
video: 36
audio: 36
support: 11
diffrhythm: 12
total: 149
vram_requirements:
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:
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:
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
Reference in New Issue View Git Blame Copy Permalink