Image-to-3D
Diffusers
Safetensors
TripoSplatImageTo3DPipeline
diffusers-3d
triposplat
3d
gaussian-splatting
Instructions to use suvadityamuk/TripoSplat-diffusers-3d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use suvadityamuk/TripoSplat-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/TripoSplat-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] - Notebooks
- Google Colab
- Kaggle
Download decoder/config.json from suvadityamuk/TripoSplat-diffusers-3d: direct link, hf CLI and curl.
- Browser
- Download file 437 Bytes
-
https://huggingface.co/suvadityamuk/TripoSplat-diffusers-3d/resolve/main/decoder/config.json
- Command line
-
hf download hf://suvadityamuk/TripoSplat-diffusers-3d/decoder/config.json
-
curl -L -o config.json https://huggingface.co/suvadityamuk/TripoSplat-diffusers-3d/resolve/main/decoder/config.json
437 Bytes
| { | |
| "_class_name": "TripoSplatGaussianDecoder", | |
| "_diffusers_version": "0.41.0.dev0", | |
| "filter_kernel_size": 0.0009, | |
| "gaussians_per_token": 32, | |
| "latent_channels": 16, | |
| "mlp_ratio": 4.0, | |
| "num_attention_heads": 16, | |
| "num_gaussian_layers": 16, | |
| "num_octree_layers": 4, | |
| "octree_depth": 8, | |
| "offset_extent": 1.5, | |
| "offset_scale": 0.05, | |
| "opacity_bias": 0.1, | |
| "rotation_scale": 0.1, | |
| "scaling_bias": 0.004, | |
| "width": 1024 | |
| } | |