Instructions to use OzzyGT/Pixal3D_Modular with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OzzyGT/Pixal3D_Modular 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_Modular", 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
File size: 412 Bytes
92011e4 | 1 2 3 4 5 6 7 | The camera projection (projection.py) and the latent normalization statistics (normalization.py) are adapted from:
Pixal3D, Copyright (c) 2026 Tencent, MIT (see LICENSE-PIXAL3D).
https://github.com/TencentARC/Pixal3D
Reference revision: f7cf384
The remaining block code is original and licensed under Apache-2.0 (see LICENSE).
The package contains no learned weights. Converted checkpoint licensing is separate.
|