Instructions to use chenguolin/DiffSplat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use chenguolin/DiffSplat with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("chenguolin/DiffSplat", 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
metadata
license: mit
datasets:
- 3DAIGC/gobjaverse
base_model:
- stabilityai/stable-diffusion-3.5-medium
- PixArt-alpha/PixArt-Sigma-XL-2-512-MS
- stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
[ICLR 2025] DiffSplat
This HuggingFace🤗 repo stores all pretrained model weights for the ICLR 2025 paper: "DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation".
For more details about usage, please refer to the official GitHub repo.