Instructions to use Qwen/Qwen-Image-Edit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Qwen/Qwen-Image-Edit 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", 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
Potentially NSFW Tag?
#23
by pavankumarbalijepalli - opened
The model seems to be able to generate NSFW content. Shouldn't we add a tag for it or mention it in the model card?
SYBAU.
They should for your IP, but they forgot. Close your eyes then.
Chinese people value practicality.
If you don't want to see NSFW content, don't look for it. It's not about NSFW, it's about not injecting personal views onto a model. You're perfectly fine with Call of Duty and watching youtube commercials and videos about weapons designed to kill or see children suffering in fucking gaza but God forbid you see explicit content. The hypocrisy is everywhere
how I can do edit img nsfw =
Bruh. I am not complaining or smn, I am just asking. Dude nevermind.
pavankumarbalijepalli changed discussion status to closed