Instructions to use YaoJiefu/multiple-characters with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use YaoJiefu/multiple-characters 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("YaoJiefu/multiple-characters", 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
This section introduces Lora from Qwen-Edit-2509, a tool for generating multiple characters. It can generate characters that fit the scene from almost any angle, and it can generate multiple characters!
Usage: Use keywords to generate characters. For example, to generate two characters sitting on a sofa watching TV, enter the keyword "Generate two people watching TV on the sofa in the image (with their backs to the camera)"; to generate a family in a living room scene, enter "Generate a cozy family of four in the image".
You can adjust the keywords as needed to clearly express the meaning.
Online workflow: https://www.runninghub.cn/post/1985510042604609538
Here is a video demonstrating Lora usage: https://www.bilibili.com/video/BV1h51qBqEqn/
- Downloads last month
- 2,182
Model tree for YaoJiefu/multiple-characters
Base model
Qwen/Qwen-Image-Edit-2509



