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]This model is trained (code-free!) on ModelScope. Thanks to ModelScope team for providing the training infra:
https://www.modelscope.ai/civision/modelTraining/
Online running link： https://www.runninghub.ai/post/2011085906899374081?inviteCode=rh-v1331
This is a user guide:
New workflow tutorial: https://youtu.be/MplcDHeDNiw
YouTube：https://youtu.be/9Vyxjty9Qao
Blibili：https://www.bilibili.com/video/BV1enrjBMECz/
For communication/cooperation, you can join the discord group to communicate： https://discord.gg/yVAVa43mWk
Project address： https://github.com/CarlMarkswx/comfyui-GaussianViewer
This project uses Apple's open-source Sharp for 3D image rotation. Project address: https://github.com/apple/ml-sharp
Using the 2509 workflow will better reproduce perspective angles, while using the 2511 workflow will result in better image consistency.
The prompt message is the default: "高斯泼溅,参考图2的场景图，修复图1的场景图透视并修复空白区域"
- Downloads last month
- 1,343
Model tree for dx8152/Qwen-Image-Edit-2511-Gaussian-Splash
Base model
Qwen/Qwen-Image-Edit-2511