license: other
license_name: multi-model-northstar-license
license_link: LICENSE
tags:
comfyui
northstar
wan2.1
video-generation
t2v
--- .
..
... <.
. << .
<< . . <<S .
<<SS . <<SS**
<<<SS . < SST *
<<<SSS . <<SSSTS**
<<<NOSS**.:.<<SSSTSS ...
<<<OSS**:<<SSAATSS** .
<<<ORRT*< SSAATSS :. SS **
.<<<<<<<< :<<<NNORRRHHTSSRRR SSSSSS *
....S<<<<NORRRNNNNNORTHHSSSRRRSSSSS**
<<<<<<<<<NORRRNSOOTTHHSSRRRSSSS**
<<<<<<<<NORRRORTTHHSARRSS **
<<<<<<<NORRRTTHHTTRRAS :.
<<<<<<NORRRRHHSTARRSSS
<<<< NORRRTHSTARSSSSS.
<<<SORRRHHH ******
<<<<NORRRTHHS **
<<<NN<NORTHHHSA***:.
...<<<<<NORTHSTAR******... .
.......****************....... . .
<< :
: :
:.
..
.
.
.
NORTHSTAR MODEL LIBRARY
Welcome, traveler. You have stumbled upon the model backbone for the Northstar project.
What is this?
This repository contains the weights and checkpoints required to run the Northstar ComfyUI suite, specifically optimized for Wan2.2 and high-end video generation.
Directory Structure
/diffusion_models: Contains the Wan2.1 14B fp8 weights.
/clip_vision: Vision encoders.
/facebook: Dinov3 pretrains.
Usage
If you are trying to use these manually, place them in your ComfyUI/models directory. If you are using the Northstar container, these are pulled automatically on launch.
Inventory Current Models
Model Files by Directory
/app/ComfyUI/models/clip_vision/clip_vision_h.safetensors (1.2G)
/app/ComfyUI/models/detection/bbox/yolov10m.onnx (59M)
/app/ComfyUI/models/detection/pose/vitpose-l-wholebody.onnx (1.2G)
/app/ComfyUI/models/diffusion_models/Wan2_2-Animate-14B_fp8_scaled_e4m3fn_KJ_v2.safetensors (17G)
/app/ComfyUI/models/facebook/dinov3-vitl16-pretrain-lvd1689m/config.json (745)
/app/ComfyUI/models/facebook/dinov3-vitl16-pretrain-lvd1689m/model.safetensors (1.2G)
/app/ComfyUI/models/facebook/dinov3-vitl16-pretrain-lvd1689m/preprocessor_config.json (585)
/app/ComfyUI/models/flashvsr/LQ_proj_in.ckpt (550M)
/app/ComfyUI/models/flashvsr/TCDecoder.ckpt (181M)
/app/ComfyUI/models/flashvsr/Wan2.1_VAE.pth (485M)
/app/ComfyUI/models/grounding-dino/groundingdino_swinb_cogcoor.pth (895M)
/app/ComfyUI/models/grounding-dino/groundingdino_swint_ogc.pth (662M)
/app/ComfyUI/models/loras/WanAnimate_relight_lora_fp16.safetensors (1.4G)
/app/ComfyUI/models/loras/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors (704M)
/app/ComfyUI/models/sam2/sam2.1_hiera_base_plus.pt (309M)
/app/ComfyUI/models/sam2/sam2.1_hiera_large.pt (857M)
/app/ComfyUI/models/sam2/sam2.1_hiera_small.pt (176M)
/app/ComfyUI/models/sam2/sam2.1_hiera_tiny.pt (149M)
/app/ComfyUI/models/sam2/sam2_hiera_base_plus.pt (309M)
/app/ComfyUI/models/sam2/sam2_hiera_large.pt (857M)
/app/ComfyUI/models/sam2/sam2_hiera_small.pt (176M)
/app/ComfyUI/models/sam2/sam2_hiera_tiny.pt (149M)
/app/ComfyUI/models/sonic/audio2bucket.pth (84M)
/app/ComfyUI/models/sonic/audio2token.pth (208M)
/app/ComfyUI/models/sonic/unet.pth (5.9G)
/app/ComfyUI/models/sonic/whisper-tiny/audio2bucket.pth (84M)
/app/ComfyUI/models/sonic/whisper-tiny/audio2token.pth (208M)
/app/ComfyUI/models/sonic/whisper-tiny/config.json (2.0K)
/app/ComfyUI/models/sonic/whisper-tiny/model.safetensors (145M)
/app/ComfyUI/models/sonic/whisper-tiny/preprocessor_config.json (181K)
/app/ComfyUI/models/sonic/yoloface_v5m.pt (81M)
/app/ComfyUI/models/text_encoders/umt5-xxl-enc-bf16.safetensors (11G)
/app/ComfyUI/models/trellis2/ckpts/shape_dec_next_dc_f16c32_fp16.json (678)
/app/ComfyUI/models/trellis2/ckpts/shape_dec_next_dc_f16c32_fp16.safetensors (905M)
/app/ComfyUI/models/trellis2/ckpts/shape_enc_next_dc_f16c32_fp16.json (653)
/app/ComfyUI/models/trellis2/ckpts/shape_enc_next_dc_f16c32_fp16.safetensors (676M)
/app/ComfyUI/models/trellis2/ckpts/slat_flow_img2shape_dit_1_3B_512_bf16.json (458)
/app/ComfyUI/models/trellis2/ckpts/slat_flow_img2shape_dit_1_3B_512_bf16.safetensors (2.5G)
/app/ComfyUI/models/trellis2/ckpts/slat_flow_imgshape2tex_dit_1_3B_512_bf16.json (458)
/app/ComfyUI/models/trellis2/ckpts/slat_flow_imgshape2tex_dit_1_3B_512_bf16.safetensors (2.5G)
/app/ComfyUI/models/trellis2/ckpts/tex_dec_next_dc_f16c32_fp16.json (705)
/app/ComfyUI/models/trellis2/ckpts/tex_dec_next_dc_f16c32_fp16.safetensors (905M)
/app/ComfyUI/models/vae/wan_2.1_vae.safetensors (243M)
Summary by File Type
safetensors: 13 files, Total size: 39G
ckpt: 2 files, Total size: 730M
pt: 9 files, Total size: 3.0G
pth: 8 files, Total size: 8.5G
onnx: 2 files, Total size: 1.3G
json: 9 files, Total size: 216K
Disk Usage by Subdirectory
54G /app/ComfyUI/models
17G /app/ComfyUI/models/diffusion_models
11G /app/ComfyUI/models/text_encoders
7.3G /app/ComfyUI/models/trellis2
6.7G /app/ComfyUI/models/sonic
3.1G /app/ComfyUI/models/flashvsr
3.0G /app/ComfyUI/models/sam2
2.1G /app/ComfyUI/models/loras
1.6G /app/ComfyUI/models/grounding-dino
1.3G /app/ComfyUI/models/detection
1.2G /app/ComfyUI/models/facebook
1.2G /app/ComfyUI/models/clip_vision
243M /app/ComfyUI/models/vae
2.7M /app/ComfyUI/models/sam3
36K /app/ComfyUI/models/microsoft
8.0K /app/ComfyUI/models/ultralytics
4.0K /app/ComfyUI/models/wav2lip
4.0K /app/ComfyUI/models/wan
4.0K /app/ComfyUI/models/vae_approx
4.0K /app/ComfyUI/models/upscale_models
4.0K /app/ComfyUI/models/unet
4.0K /app/ComfyUI/models/unclip
4.0K /app/ComfyUI/models/style_models
4.0K /app/ComfyUI/models/sams
4.0K /app/ComfyUI/models/photomaker
4.0K /app/ComfyUI/models/onnx
4.0K /app/ComfyUI/models/model_patches
4.0K /app/ComfyUI/models/latent_upscale_models
4.0K /app/ComfyUI/models/hypernetworks
4.0K /app/ComfyUI/models/gligen
4.0K /app/ComfyUI/models/embeddings
4.0K /app/ComfyUI/models/diffusers
4.0K /app/ComfyUI/models/controlnet
4.0K /app/ComfyUI/models/configs
4.0K /app/ComfyUI/models/clip
4.0K /app/ComfyUI/models/checkpoints
4.0K /app/ComfyUI/models/audio_encoders
4.0K /app/ComfyUI/models/annotator
sonic/ - 10 files found
Total size: 6.7G
├─ RIFE/flownet.pkl (12M)
├─ audio2bucket.pth (84M)
├─ audio2token.pth (208M)
├─ unet.pth (5.9G)
├─ whisper-tiny/audio2bucket.pth (84M)
├─ whisper-tiny/audio2token.pth (208M)
├─ whisper-tiny/config.json (2.0K)
├─ whisper-tiny/model.safetensors (145M)
├─ whisper-tiny/preprocessor_config.json (181K)
├─ yoloface_v5m.pt (81M)
WARNING: This directory is NOT in any download sccript!
You may need to add these models manually or update the scripts.
flashvsr/ - 21 files found
Total size: 3.1G
├─ .cache/huggingface/.gitignore (1)
├─ .cache/huggingface/download/.gitattributes.lock (0)
├─ .cache/huggingface/download/.gitattributes.metadata (104)
├─ .cache/huggingface/download/Gz7dnp1Rz1AvSoJz3oTa3zhJyeU=.e224bdcf2f52745cbf4d393ff5374c2ba09e90285d5d19062d2bf63b915b6161.incomplete (0)
├─ .cache/huggingface/download/LQ_proj_in.ckpt.lock (0)
├─ .cache/huggingface/download/LQ_proj_in.ckpt.metadata (128)
├─ .cache/huggingface/download/OZTShqo6Di7rh0SEswnfwSjKa9w=.38071ab59bd94681c686fa51d75a1968f64e470262043be31f7a094e442fd981.incomplete (0)
├─ .cache/huggingface/download/README.md.lock (0)
├─ .cache/huggingface/download/README.md.metadata (103)
├─ .cache/huggingface/download/TCDecoder.ckpt.lock (0)
├─ .cache/huggingface/download/TCDecoder.ckpt.metadata (128)
├─ .cache/huggingface/download/Wan2.1_VAE.pth.lock (0)
├─ .cache/huggingface/download/Wan2.1_VAE.pth.metadata (128)
├─ .cache/huggingface/download/_CczzmKcH-_cdsOQdK0AVO__wCQ=.d6d011cdaaba6a52645086caa08fa04124e746f6ca568140a24007591142bfd2.incomplete (550M)
├─ .cache/huggingface/download/diffusion_pytorch_model_streaming_dmd.safetensors.lock (0)
├─ .cache/huggingface/download/pTDf0BK3_qbvNdS6AT6G_j3GCnw=.bd28180edcf3446c028e32fc6b731a80bf7e4da2ab4caac3186b9499964d37be.incomplete (1.3G)
├─ .gitattributes (1.5K)
├─ LQ_proj_in.ckpt (550M)
├─ README.md (9.6K)
├─ TCDecoder.ckpt (181M)
├─ Wan2.1_VAE.pth (485M)
sam2/ - 10 files found
Total size: 3.0G
├─ download_models.sh (1.4K)
├─ sam2.1_hiera_base_plus.pt (309M)
├─ sam2.1_hiera_large.pt (857M)
├─ sam2.1_hiera_small.pt (176M)
├─ sam2.1_hiera_tiny.pt (149M)
├─ sam2_hiera_base_plus.pt (309M)
├─ sam2_hiera_large.pt (857M)
├─ sam2_hiera_small.pt (176M)
├─ sam2_hiera_tiny.pt (149M)
├─ urls.txt (992)
sam3/ - 2 files found
Total size: 2.7M
├─ assets/bpe_simple_vocab_16e6.txt.gz (1.3M)
├─ assets/bpe_simple_vocab_16e6.txt.gz.1 (1.3M)
facebook/ - 8 files found
Total size: 1.2G
├─ dinov3-vitl16-pretrain-lvd1689m/LICENSE (7.4K)
├─ dinov3-vitl16-pretrain-lvd1689m/LICENSE.md (7.4K)
├─ dinov3-vitl16-pretrain-lvd1689m/README (15K)
├─ dinov3-vitl16-pretrain-lvd1689m/README.md (15K)
├─ dinov3-vitl16-pretrain-lvd1689m/config.json (745)
├─ dinov3-vitl16-pretrain-lvd1689m/gitattributes (1.5K)
├─ dinov3-vitl16-pretrain-lvd1689m/model.safetensors (1.2G)
├─ dinov3-vitl16-pretrain-lvd1689m/preprocessor_config.json (585)
grounding-dino/ - 4 files found
Total size: 1.6G
├─ GroundingDINO_SwinB.cfg.py (1007)
├─ GroundingDINO_SwinT_OGC.cfg.py (1006)
├─ groundingdino_swinb_cogcoor.pth (895M)
├─ groundingdino_swint_ogc.pth (662M)
Special Check: Microsoft/TRELLIS models
Found microsoft/ directory. Checking subdirectories...
microsoft/TRELLIS-image-large/
microsoft/TRELLIS.2-4B/
Model / Component Creator Original License
Wan2.1 14B Alibaba / Wan-Video CreativeML OpenRAIL-M
DinoV3 Meta / Facebook Apache 2.0
Trellis / Uni-6DoF Microsoft MIT License
Grounding-DINO IDEA-Research Apache 2.0
Custom Nodes/Scripts alphanumeric2 [MIT / GPLv3]