Instructions to use YaoJiefu/Add-light-and-shadow with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use YaoJiefu/Add-light-and-shadow 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/Add-light-and-shadow", 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 LoRa model was trained on ModelScope, which is an excellent platform that you can also use to train your model.
https://www.modelscope.cn/aigc/modelTraining
This Lora and workflow can add a variety of rich and cool lighting effects to characters. Whatever lighting effects you want, it can add them for you.Besides adding lighting effects to close-up portraits, everyday tourist photos and photos taken in daily life can also have lighting effects added, serving as a post-processing tool.
Prompt words:
“使用(这里写光影的名称)对图中人物进行重新打光”
Online running link:https://www.runninghub.cn/post/1993482633977987073?inviteCode=phm6nhbr
This is a user guide:
Blibili:https://www.bilibili.com/video/BV1kAU8BkEn3/
By adding light and shadow, we can not only obtain beautiful images of people with light and shadow, but also process these images, add text and do layout design, turning these images into posters to convey some content.

- Downloads last month
- 5
Model tree for YaoJiefu/Add-light-and-shadow
Base model
Qwen/Qwen-Image-Edit-2509






