Text-to-Image
Diffusers
Safetensors
English
image-generation
class-conditional
imagenet
pixelflow
flow-matching
Instructions to use BiliSakura/PixelFlow-diffusers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BiliSakura/PixelFlow-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/PixelFlow-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "golden retriever" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Download PixelFlow-256/transformer/config.json from BiliSakura/PixelFlow-diffusers: direct link, hf CLI and curl.
- Browser
- Download file 362 Bytes
-
https://huggingface.co/BiliSakura/PixelFlow-diffusers/resolve/main/PixelFlow-256/transformer/config.json
- Command line
-
hf download hf://BiliSakura/PixelFlow-diffusers/PixelFlow-256/transformer/config.json
-
curl -L -o config.json https://huggingface.co/BiliSakura/PixelFlow-diffusers/resolve/main/PixelFlow-256/transformer/config.json
362 Bytes
| { | |
| "_class_name": "PixelFlowTransformer2DModel", | |
| "_diffusers_version": "0.36.0", | |
| "attention_bias": true, | |
| "attention_head_dim": 72, | |
| "cross_attention_dim": null, | |
| "depth": 28, | |
| "dropout": 0.0, | |
| "in_channels": 3, | |
| "init_weights": false, | |
| "num_attention_heads": 16, | |
| "num_classes": 1000, | |
| "out_channels": 3, | |
| "patch_size": 4, | |
| "sample_size": 256 | |
| } | |