Image-to-Image
Diffusers
GGUF
English
Chinese
image-editing
consistency
aesthetics
DiT
Qwen-Image
ValiantCat
Instructions to use joyfox/Qwen-Image-Edit-MeiTu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use joyfox/Qwen-Image-Edit-MeiTu 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("joyfox/Qwen-Image-Edit-MeiTu", 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] - Notebooks
- Google Colab
- Kaggle
Will the gguf version be available?
#2
by Cemrek - opened
Hey! It's great to see this model here, and I can't wait to use it, but my system isn't powerful enough. Will there be lower versions or a GGUF version available? For VRAM-friendly users.
just trying a MeiTu NSWF 5.3, in first i'll try only the Q5_KM and compare to Pht00t's original, maybe we get some better facial consistency.