Instructions to use xixircc/MetaRigCapture with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use xixircc/MetaRigCapture with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("xixircc/MetaRigCapture", 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
| data: | |
| chunk_size: 150 | |
| json_files: | |
| - ./jsons/blow.json | |
| - ./jsons/eyebrow.json | |
| - ./jsons/pout.json | |
| - ./jsons/nersemble_front.json | |
| - ./jsons/yk_cap.json | |
| - ./jsons/xnemo_transfer.json | |
| mount_prefix: /aliyun-oss | |
| num_workers: 4 | |
| oss_prefix: oss://aigcdevwlcb | |
| seed: 42 | |
| val_ratio: 0.1 | |
| model: | |
| mask_feature_dim: 64 | |
| motion_dim: 512 | |
| rigs_dim: 169 | |
| tcn_config: | |
| depth: 6 | |
| dropout: 0.1 | |
| hidden: 1024 | |
| train: | |
| batch_size: 16 | |
| brow_boost_factor: 2.0 | |
| enable_brow_boost: true | |
| learning_rate: 0.0001 | |
| log_interval: 50 | |
| max_grad_norm: 1.0 | |
| mixed_precision: fp16 | |
| num_epochs: 100 | |
| output_dir: /home/deepspeed/workdir/FaceCapture/outputs/motion_mask_rig_weighted_2025-12-04_17-43-32 | |
| symmetric_weight: 1.0 | |
| use_scheduler: true | |
| use_symmetric_loss: true | |
| weight_decay: 0.0001 | |