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.
NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
| Date | Stars |
|---|---|
| 2026-07-31 | 428 |
| 2026-08-03 | 428 |
| 2026-08-06 | 428 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Mix-of-Show 🚩🚩🚩: Main branch for community has been released (keep updating the main branch). ------ Official codes for Mix-of-Show. This branch is for application, including simplified codes, memory/speed optimization and performance improvement. For research purpose, please refer to original [research branch](https://github.com/TencentARC/Mix-of-Show/tree/research_branch) (paper results, evaluation, and comparison methods). **[NeurIPS 2023]**- **[Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models](https://arxiv.org/abs/2305.18292)** <br/> [Yuchao Gu](https://ycgu.site/), [Xintao Wang](https://xinntao.github.io/), [Jay Zhangjie Wu](https://zhangjiewu.github.io/), [Yunjun Shi](https://yujun-shi.github.io/), [Yunpeng Chen](https://cypw.github.io/), Zihan Fan, Wuyou Xiao, [Rui Zhao](https://ruizhaocv.github.io/), Shuning Chang, [Weijia Wu](https://weijiawu.github.io/), [Yixiao Ge](https://geyixiao.com/), Ying Shan, [Mike Zheng Shou](https://sites.google.com/view/showlab) <br/> [](https://showlab.github.io/Mix-of-Show/)[](https://arxiv.org/abs/2305.18292) ## 📋 Results ### Single-Concept Results Difference from LoRA: 1) In ED-LoRA, the embedding (LoRA weight=0) already encodes stable identity (use harry potter as example):  2) Based on the ED-LoRA, we can support multi-concept fusion without much identity loss. ### Multi-Concept Results **Concept List:**  **Anime Character**:  **Real Character**:   ------ Conneting Mix-of-Show with Stable Diffusion Video for Animatation: https://github.com/TencentARC/Mix-of-Show/assets/31696690/5a677e99-2c86-41dc-a9da-ba92b3155717 ## 🚩 Updates/Todo List - [ ] StableDiffusion XL support. - [ ] Colab Demo. - [x] Oct. 8, 2023. Add Attention Reg & Quality Improvement. - [x] Oct. 3, 2023. Release Main Branch for Community. - [x] Jun. 12, 2023. Research Code Released. Please switch to [research branch](https://github.com/TencentARC/Mix-of-Show/tree/research_branch). ## :wrench: Dependencies and Installation - Python >= 3.9 (Recommend to use [Anaconda](https://www.anaconda.com/download/#linux) or [Miniconda](https://docs.conda.io/en/latest/miniconda.html)) - Diffusers==0.19.3 - XFormer (is recommend to save memory) ## ⏬ Pretrained Model and Data Preparation ### Pretrained Model Preparation We adopt the [ChilloutMix](https://civitai.com/models/6424/chilloutmix) for real-world concepts, and [Anything-v4](https://huggingface.co/andite/anything-v4.0) for anime concepts. ```bash git clone https://github.com/TencentARC/Mix-of-Show.git cd experiments/pretrained_models # Diffusers-version ChilloutMix git-lfs clone https://huggingface.co/windwhinny/chilloutmix.git # Diffusers-version Anything-v4 git-lfs clone https://huggingface.co/andite/anything-v4.0.git ``` ### Data Preparation Note: Data selection and tagging are important in single-concept tuning. We strongly recommend checking the data processing in [sd-scripts](https://github.com/kohya-ss/sd-scripts). **In our ED-LoRA, we do not require any regularization dataset.** The detailed dataset preparation steps can re
Excerpt of 10,942 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a53aea5d25f83f20, llm:Repository description: 'NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models' (Python). Focus on low-rank adaptation for customizing diffusion models.
matched fp:a53aea5d25f83f20, llm:Repository description: 'NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models' (Python). Focus on low-rank adaptation for customizing diffusion models.
matched fp:a53aea5d25f83f20, llm:Repository description: 'NeurIPS 2023, Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models' (Python). Focus on low-rank adaptation for customizing diffusion models.