Unconditional Image Generation
Diffusers
Safetensors
English
deco
image-generation
class-conditional
imagenet
Instructions to use BiliSakura/DeCo-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/DeCo-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/DeCo-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "golden retriever" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
File size: 171 Bytes
9dc3cb9 | 1 2 3 4 5 6 7 8 9 10 | {
"_class_name": "DeCoPatchDecoderModel",
"hidden_size_x": 32,
"in_channels": 3,
"max_freqs": 8,
"num_res_blocks": 3,
"patch_size": 16,
"z_channels": 1152
}
|