Diffusers
Safetensors
English
motionbricks
modular-diffusers
motion-generation
motion-inbetweening
soma
Instructions to use OzzyGT/motionbricks_soma_diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OzzyGT/motionbricks_soma_diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OzzyGT/motionbricks_soma_diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Download pose_model/config.json from OzzyGT/motionbricks_soma_diffusers: direct link, hf CLI and curl.
- Browser
- Download file 503 Bytes
-
https://huggingface.co/OzzyGT/motionbricks_soma_diffusers/resolve/main/pose_model/config.json
- Command line
-
hf download hf://OzzyGT/motionbricks_soma_diffusers/pose_model/config.json
-
curl -L -o config.json https://huggingface.co/OzzyGT/motionbricks_soma_diffusers/resolve/main/pose_model/config.json
503 Bytes
| { | |
| "_class_name": "MotionBricksPoseTransformer", | |
| "_diffusers_version": "0.41.0", | |
| "auto_map": { | |
| "AutoModel": "transformer_motionbricks.MotionBricksPoseTransformer" | |
| }, | |
| "code_embed_dim": 32, | |
| "codebook_size": 16, | |
| "ff_dim": 2048, | |
| "frames_per_token": 4, | |
| "hidden_dim": 1024, | |
| "length_embed_dim": 128, | |
| "max_tokens": 16, | |
| "min_tokens": 6, | |
| "num_heads": 16, | |
| "num_heads_codebook": 5, | |
| "num_layers": 16, | |
| "pose_dim": 268, | |
| "root_dim": 4, | |
| "root_embed_dim": 256, | |
| "token_dim": 640 | |
| } | |