Instructions to use YaoJiefu/Line-drawing-generates-special-effects with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use YaoJiefu/Line-drawing-generates-special-effects 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/Line-drawing-generates-special-effects", 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, and I'm very grateful to the ModelScope platform! https://www.modelscope.cn/aigc/modelTraining
The new tool, Lora, allows you to generate product effects simply by drawing a line around the product. It's an incredibly powerful tool for creating product effects, eliminating tedious steps and solving the problem of previously complicated effect creation.
Keyword writing: “根据图中画出的(黑色或白色)线条(形状、位置以及范围)生成(XXXXX的特效)”
“Generate (XXXXX special effects) based on the (black or white) lines (shape, position, and range) drawn in the image”
*Simply replace the "XXX" part in parentheses with the effect name. You can deduce the effect name from images on various AI platforms; I'm using "豆包" here.
Online running link:
https://www.runninghub.cn/post/2001941830977634306?inviteCode=phm6nhbr
This is a user guide: Blibili:https://www.bilibili.com/video/BV1BEBwBaENy/
It's very easy to use, generates great effects, and matches the product.
A wide variety of special effects can be generated perfectly, including lighting effects, airflow, water jets, technological effects, and even fluid effects.
- Downloads last month
- 6
Model tree for YaoJiefu/Line-drawing-generates-special-effects
Base model
Qwen/Qwen-Image-Edit-2509


















