Instructions to use suvadityamuk/TRELLIS-image-large-diffusers-3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use suvadityamuk/TRELLIS-image-large-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-image-large-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-image-large-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
suvadityamuk HF Staff
Convert microsoft/TRELLIS-image-large with diffusers-3d 0.1.0.dev0
5e1711c verified Download mesh_decoder/config.json from suvadityamuk/TRELLIS-image-large-diffusers-3d: direct link, hf CLI and curl.
- Browser
- Download file 448 Bytes
-
https://huggingface.co/suvadityamuk/TRELLIS-image-large-diffusers-3d/resolve/main/mesh_decoder/config.json
- Command line
-
hf download hf://suvadityamuk/TRELLIS-image-large-diffusers-3d/mesh_decoder/config.json
-
curl -L -o config.json https://huggingface.co/suvadityamuk/TRELLIS-image-large-diffusers-3d/resolve/main/mesh_decoder/config.json
448 Bytes
| { | |
| "_class_name": "TrellisSLatMeshDecoder", | |
| "_diffusers_version": "0.41.0.dev0", | |
| "attn_mode": "swin", | |
| "latent_channels": 8, | |
| "mlp_ratio": 4, | |
| "model_channels": 768, | |
| "num_blocks": 12, | |
| "num_groups": 32, | |
| "num_head_channels": 64, | |
| "num_heads": 12, | |
| "pe_mode": "ape", | |
| "qk_rms_norm": false, | |
| "representation_config": { | |
| "use_color": true | |
| }, | |
| "resolution": 64, | |
| "use_checkpoint": false, | |
| "use_fp16": true, | |
| "window_size": 8 | |
| } | |