Instructions to use OzzyGT/Pixal3D with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OzzyGT/Pixal3D 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/Pixal3D", 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 sparse_structure_flow_model/config.json from OzzyGT/Pixal3D: direct link, hf CLI and curl.
- Browser
- Download file 402 Bytes
-
https://huggingface.co/OzzyGT/Pixal3D/resolve/main/sparse_structure_flow_model/config.json
- Command line
-
hf download hf://OzzyGT/Pixal3D/sparse_structure_flow_model/config.json
-
curl -L -o config.json https://huggingface.co/OzzyGT/Pixal3D/resolve/main/sparse_structure_flow_model/config.json
402 Bytes
| { | |
| "_class_name": "Pixal3DTransformer3DModel", | |
| "_diffusers_version": "0.41.0.dev0", | |
| "cond_channels": 1024, | |
| "dense": true, | |
| "in_channels": 8, | |
| "mlp_ratio": 5.3334, | |
| "model_channels": 1536, | |
| "num_blocks": 30, | |
| "num_heads": 12, | |
| "out_channels": 8, | |
| "proj_in_channels": null, | |
| "qk_rms_norm": true, | |
| "qk_rms_norm_cross": true, | |
| "resolution": 16, | |
| "rope_freq": [ | |
| 1.0, | |
| 10000.0 | |
| ] | |
| } | |