Instructions to use dx8152/Qwen-Edit-2509-Multiple-angles with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dx8152/Qwen-Edit-2509-Multiple-angles 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("dx8152/Qwen-Edit-2509-Multiple-angles") 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 Settings
- Draw Things
How to be compatible with lighting lora?
#34
by tayton - opened
Thank you for your work. I would like to ask how you ensure compatibility with lighting lora during training. The lora I trained myself does not perform as expected under lighting lora.
Thank you for your work. I would like to ask how you ensure compatibility with lighting lora during training. The lora I trained myself does not perform as expected under lighting lora.
I don't know either. I'm using ModelScope's default training mode. Is it because you're training with bf32 while we're using bf16?