Unconditional Image Generation
Diffusers
Safetensors
English
bitdance
imagenet
class-conditional
custom-pipeline
Instructions to use BiliSakura/BitDance-ImageNet-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/BitDance-ImageNet-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/BitDance-ImageNet-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": "BitDanceImageNetTransformer", | |
| "_diffusers_version": "0.36.0", | |
| "architecture": "BitDance-B", | |
| "parallel_num": 4, | |
| "resolution": 256, | |
| "down_size": 16, | |
| "latent_dim": 32, | |
| "num_classes": 1000, | |
| "source_checkpoint": "/data/projects/BitDance/models/shallowdream204/BitDance-ImageNet/BitDance_B_4x.pt", | |
| "source_key": "ema", | |
| "runtime_impl": "model_parallel.py", | |
| "parallel_mode": "patch", | |
| "time_schedule": "logit_normal", | |
| "time_shift": 1.0, | |
| "p_std": 1.0, | |
| "p_mean": 0.0 | |
| } | |