Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official Implementation of 'Inserting Anybody in Diffusion Models via Celeb Basis'
| Date | Stars |
|---|---|
| 2026-08-05 | 255 |
| 2026-08-21 | 252 |
| 2026-10-02 | 252 |
| 2026-11-04 | 252 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
## Inserting Anybody in Diffusion Models via Celeb Basis (NeurIPS 23)
<a href='https://arxiv.org/abs/2306.00926'><img src='https://img.shields.io/badge/ArXiv-PDF-red'></a>
<a href='https://celeb-basis.github.io'><img src='https://img.shields.io/badge/Project-Page-Green'></a>
[](https://colab.research.google.com/github/ygtxr1997/CelebBasis/blob/main/notebooks/CelebBasisColab.ipynb)
<div>
<span class="author-block">
<a href="https://ygtxr1997.github.io/" target="_blank">Ge Yuan</a><sup>1,2</sup></span>,
<span class="author-block">
<a href="http://vinthony.github.io/" target="_blank">Xiaodong Cun</a><sup>2</sup></span>,
<span class="author-block">
<a href="https://yzhang2016.github.io" target="_blank">Yong Zhang</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=ym_t6QYAAAAJ&hl=zh-CN&oi=sra" target="_blank">Maomao Li</a><sup>2,*</sup>,
</span>
<span class="author-block"><a href="https://chenyangqiqi.github.io/" target="_blank">Chenyang Qi</a><sup>3,2</sup></span>, <br>
<span class="author-block">
<a href="https://xinntao.github.io/" target="_blank">Xintao Wang</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?hl=zh-CN&user=4oXBp9UAAAAJ" target="_blank">Ying Shan</a><sup>2</sup>,
</span>
<span class="author-block">
<a href="https://scholar.google.com/citations?user=CCUQi50AAAAJ" target="_blank">Huicheng Zheng</a><sup>1,*</sup>
</span> (* Corresponding Authors)
</div>
<div class="is-size-5 publication-authors">
<span class="author-block">
<sup>1</sup> Sun Yat-sen University
<sup>2</sup> Tencent AI Lab
<sup>3</sup> HKUST </span>
</div>
<br>
**TL;DR: Intergrating a unique individual into the pre-trained diffusion model with:**
✅ just <b>one</b> facial photograph
✅ only <b>1024</b> learnable parameters
✅ in <b>3</b> minutes tunning
</br>✅ Textural-Inversion compatibility ✅ Genearte and interact with other (new person) concepts </br>
### Updates
- **2023/10/11:** Our [paper](https://arxiv.org/abs/2306.00926) is accepted by NIPS'23!
- **2023/06/23:** Code released!
### How It Work
First, we collect about 1,500 celebrity names as the initial collection. Then, we manually filter the initial one to m = 691 names, based on the synthesis quality of text-to-image diffusion model(stable-diffusion} with corresponding name prompt. Later, each filtered name is tokenized and encoded into a celeb embedding group. Finally, we conduct Principle Component Analysis to build a compact orthogonal basis.
We then personalize the model using input photo. During training~(left), we optimize the coefficients of the celeb basis with the help of a fixed face encoder. During inference~(right), we combine the learned personalized weights and shared celeb basis to generate images with the input identity.
More details can be found in our [project page](https://celeb-basis.github.io).
### Setup
Our code mainly bases on [Textual Inversion](https://github.com/rinongal/textual_inversion).
We add some environment requirements for Face Alignment & Recognition to the original environment of [Textual Inversion](https://github.com/rinongal/textual_inversion).
To set up our environment, please run:
```shell
conda env create -f enviExcerpt of 10,421 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ba97f7c07b7ce9f6, llm:Repository description: 'Official Implementation of "Inserting Anybody in Diffusion Models via Celeb Basis"' — indicates code for modifying diffusion models for faces/celebrity basis insertion (computer vision / image generation).
matched fp:ba97f7c07b7ce9f6, llm:Repository description: 'Official Implementation of "Inserting Anybody in Diffusion Models via Celeb Basis"' — indicates code for modifying diffusion models for faces/celebrity basis insertion (computer vision / image generation).
matched fp:ba97f7c07b7ce9f6, llm:Repository description: 'Official Implementation of "Inserting Anybody in Diffusion Models via Celeb Basis"' — indicates code for modifying diffusion models for faces/celebrity basis insertion (computer vision / image generation).