Instructions to use OPPOer/Qwen-Image-Edit-2509-Pruning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OPPOer/Qwen-Image-Edit-2509-Pruning 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("OPPOer/Qwen-Image-Edit-2509-Pruning", 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
smaller size model
#1
by milely - opened
Thanks for the open-source pruning model. Are there any smaller pruning models available?
Thanks for your attention. Recently, there hasn't been much time invested in optimization. The preliminary conclusion is that the pruning of the editing I2I model is more sensitive than that of the T2I model, necessitating the development of further tuning strategies to compress it into a smaller model.