Feature Extraction
Diffusers
Safetensors
English
autoencoder
vision-foundation-model
dinov2
dinov3
mae
siglip2
pae
Instructions to use BiliSakura/PAE-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/PAE-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/PAE-diffusers", 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
| { | |
| "_class_name": "LightningDiT2DModel", | |
| "depth": 28, | |
| "hidden_size": 1152, | |
| "in_channels": 32, | |
| "input_size": 16, | |
| "num_classes": 1000, | |
| "num_heads": 16, | |
| "patch_size": 1, | |
| "use_qknorm": true, | |
| "use_rmsnorm": true, | |
| "use_rope": true, | |
| "use_swiglu": true, | |
| "wo_shift": false | |
| } | |