Instructions to use Qwen/Qwen-Image-Edit-2511 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Qwen/Qwen-Image-Edit-2511 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-2511", 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] - Inference
- Notebooks
- Google Colab
- Kaggle
Changes in LoRA order?
#27
by demokrit2024 - opened
I've noticed some significant change in the ComfyUI templates from 2509 to 2511 and wonder if this is intended:
In initial ImageEdit and 2509 the order was: Load gguf->Load4steplightning Lora(->apply additional loras)->Aura->CFGNorm->Ksampler
Now it seems to be: Load gguf->Aura->CFGNorm->Load4steplightning->Ksampler
Also Aura strength increased from 3.0 to 3.1
Is this intended? And where would I put more additional Loras? In general I would still assume to do it before the Aura?
Maybe someone can give a clear guide here ;) Thanks!