Instructions to use suvadityamuk/TRELLIS.2-4B-diffusers-3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use suvadityamuk/TRELLIS.2-4B-diffusers-3d with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("suvadityamuk/TRELLIS.2-4B-diffusers-3d", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Trellis
How to use suvadityamuk/TRELLIS.2-4B-diffusers-3d with Trellis:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download sparse_structure_flow_model/config.json from suvadityamuk/TRELLIS.2-4B-diffusers-3d: direct link, hf CLI and curl.
- Browser
- Download file 513 Bytes
-
https://huggingface.co/suvadityamuk/TRELLIS.2-4B-diffusers-3d/resolve/main/sparse_structure_flow_model/config.json
- Command line
-
hf download hf://suvadityamuk/TRELLIS.2-4B-diffusers-3d/sparse_structure_flow_model/config.json
-
curl -L -o config.json https://huggingface.co/suvadityamuk/TRELLIS.2-4B-diffusers-3d/resolve/main/sparse_structure_flow_model/config.json
513 Bytes
| { | |
| "_class_name": "Trellis2SparseStructureFlowModel", | |
| "_diffusers_version": "0.41.0.dev0", | |
| "cond_channels": 1024, | |
| "dtype": "bfloat16", | |
| "in_channels": 8, | |
| "initialization": "scaled", | |
| "mlp_ratio": 5.3334, | |
| "model_channels": 1536, | |
| "num_blocks": 30, | |
| "num_head_channels": 64, | |
| "num_heads": 12, | |
| "out_channels": 8, | |
| "pe_mode": "rope", | |
| "qk_rms_norm": true, | |
| "qk_rms_norm_cross": true, | |
| "resolution": 16, | |
| "rope_freq": [ | |
| 1.0, | |
| 10000.0 | |
| ], | |
| "share_mod": true, | |
| "use_checkpoint": false | |
| } | |