Instructions to use OPPOer/Qwen-Image-Edit-Pruning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OPPOer/Qwen-Image-Edit-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-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
Not working with loras?
#1
by diveren2010 - opened
I dont think this works with lightning loras.
In our current open-source version, we have integrated lightning loras, so there is no need to add an additional accelerated LoRA.
Is version without lightning LoRA available?
Qwen-Image-Edit-2509-Pruning is available: https://huggingface.co/OPPOer/Qwen-Image-Edit-2509-Pruning/tree/main/Qwen-Image-Edit-2509-14B
This one isn't? Original QIE is better than 2509 for certain tasks
We will update the QIE version without lighting LoRA in the next few days