Instructions to use hustvl/PixelHacker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use hustvl/PixelHacker with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("hustvl/PixelHacker", 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
metadata
license: mit
《PixelHacker: Image Inpainting with Structural and Semantic Consistency》
Project Page: https://hustvl.github.io/PixelHacker
Paper: https://arxiv.org/abs/2504.20438
Code: https://github.com/hustvl/PixelHacker
weight: https://huggingface.co/hustvl/PixelHacker/tree/main