Instructions to use VAST-AI/HoloPart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use VAST-AI/HoloPart with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("VAST-AI/HoloPart", torch_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
| { | |
| "_class_name": "PartEncoder", | |
| "_diffusers_version": "0.30.3", | |
| "dim": 512, | |
| "embed_frequency": 8, | |
| "embed_include_pi": false, | |
| "embedding_type": "frequency", | |
| "init_weights": null, | |
| "noise_level": null, | |
| "num_attention_heads": 8, | |
| "num_layers": 8, | |
| "num_tokens": 2048, | |
| "part_feature_channels": 3, | |
| "part_local": true, | |
| "position_channels": 3, | |
| "whole_feature_channels": 4 | |
| } | |