Instructions to use lrzjason/QwenEdit-Anything2Real_Alpha with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lrzjason/QwenEdit-Anything2Real_Alpha 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("Qwen/Qwen-Image-Edit-2509", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("lrzjason/QwenEdit-Anything2Real_Alpha") 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] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
Feedback on unexpected changes of face and bodily fluids
#11
by daijava - opened
Hi team,
A few observations on this Lora:
When converting images to realistic photos, the Lora tends to alter facial features significantly β without detailed prompts, the original expression, mouth closure, eye gaze, and pupil color are often not preserved.
Also, unless explicitly described, bodily fluids present in the original image are usually removed in the output.
Just wanted to share these findings. Thanks for your work!