Instructions to use peteromallet/Qwen-Image-Edit-InStyle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use peteromallet/Qwen-Image-Edit-InStyle 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") pipe.load_lora_weights("peteromallet/Qwen-Image-Edit-InStyle") 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
- Local Apps
- Draw Things
how to use for style transfer?
#6
by krigeta - opened
any workflow where we can transfer the style of one image to another image without changing its composition? for e.g. real life image and a style image of anime then turning that real life image to anime or vice versa?
the same question. and also in the attached workflow it turns out that:
Prompt execution failed
Prompt outputs failed validation:
ReferenceLatent:
- Return type mismatch between linked nodes: latent, received_type(VAE) mismatch input_type(LATENT)
ReferenceLatent: - Return type mismatch between linked nodes: latent, received_type(VAE) mismatch input_type(LATENT)
ReferenceLatent: - Return type mismatch between linked nodes: latent, received_type(VAE) mismatch input_type(LATENT)