Summary of Jiehua Paintings Style Feature Extracting Model Using Stable Diffusion with Controlnet, by Yujia Gu et al.
JieHua Paintings Style Feature Extracting Model using Stable Diffusion with ControlNet
by Yujia Gu, Haofeng Li, Xinyu Fang, Zihan Peng, Yinan Peng
First submitted to arxiv on: 21 Aug 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed approach utilizes a novel Fine-tuned Stable Diffusion Model with ControlNet (FSDMC) to refine depiction techniques from artists’ Jiehua. The model is trained on an open-source dataset of Jiehua artist’s work, manually constructed in the format of (Original Image, Canny Edge Features, Text Prompt). The FSDMC outperforms CycleGAN, a mainstream style transfer model, achieving an FID of 3.27 and surpassing it in expert evaluation. This demonstrates the model’s effectiveness in extracting Jiehua’s style features while preserving original semantic information. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The study uses a special computer model to make art look more like traditional Chinese paintings called Jiehua. They train this model on lots of examples of Jiehua and compare it to another popular model, CycleGAN. The new model does a better job of capturing the style of Jiehua and also keeps the original meaning of the image. |
Keywords
» Artificial intelligence » Diffusion model » Prompt » Style transfer
