Instructions to use yhx12/DiffThinker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use yhx12/DiffThinker with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("yhx12/DiffThinker", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Improve model card for DiffThinker: Add metadata, links, and usage details
#1
by nielsr HF Staff - opened
Hi! I'm Niels from the Hugging Face community science team. I've updated the model card for DiffThinker to enhance its discoverability and provide more comprehensive information.
This PR includes the following improvements:
- Metadata: Added
pipeline_tag: image-to-imageandlibrary_name: diffusersto enable automated usage snippets and improve searchability. - Links: Added a direct link to the official GitHub repository for easy access to the code.
- Content: Incorporated a concise summary of the model's purpose, its key features (efficiency, controllability, native parallelism, and collaboration), and detailed "Quick Start" and "Inference & Evaluation" sections with code snippets from the original GitHub README.
- Citation: Added a BibTeX entry for proper academic attribution.
These changes will help users better understand and utilize the DiffThinker model.
yhx12 changed pull request status to merged