Instructions to use dx8152/Qwen-Image-Edit-2511-Gaussian-Splash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dx8152/Qwen-Image-Edit-2511-Gaussian-Splash 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("dx8152/Qwen-Image-Edit-2511-Gaussian-Splash") 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
Question: Any plans to reproduce with Flux Klein 4/9B?
#3
by Flakily6416 - opened
I'm asking because they appear to have the same capabilities as Qwen, but are sooooo much smaller/faster.
I'm asking because they appear to have the same capabilities as Qwen, but are sooooo much smaller/faster.
I'm training and testing this, but the results don't seem to be very good. I'm still trying to find the reason.
I'm asking because they appear to have the same capabilities as Qwen, but are sooooo much smaller/faster.
I'm training and testing this, but the results don't seem to be very good. I'm still trying to find the reason.
Good luck! I hope you find the reason, because the Qwen one is very useful!