Image-to-Image
Diffusers
Safetensors
Diffusion Single File
comfyui
distillation
LoRA
lora
Qwen-Image
Qwen-Image-Edit
Instructions to use lightx2v/Qwen-Image-Edit-2511-Lightning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use lightx2v/Qwen-Image-Edit-2511-Lightning 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") pipe.load_lora_weights("lightx2v/Qwen-Image-Edit-2511-Lightning") 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] - Diffusion Single File
How to use lightx2v/Qwen-Image-Edit-2511-Lightning with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
8steps vs 4steps
#11
by Ciledselon - opened
i got broken results using qwen edit 2511 8steps with res_2s_ode sampler and beta57 scheduler but the results were fine using the 4steps one. The 4steps one also yields better quality using default sampler and scheduler (euler and simple)
flux.2d much better
flux2d & Flux2D.9B is worlds better and distilled right out of the box. Do yourself a favor and don't use qwen anymore. Qwen is now dead thanks to the Flux small models.