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.
[SIGGRAPH Asia 2024] ReVersion: Diffusion-Based Relation Inversion from Images
| Date | Stars |
|---|---|
| 2026-07-24 | 503 |
| 2026-07-25 | 503 |
| 2026-07-28 | 503 |
| 2026-07-30 | 503 |
| 2026-08-06 | 503 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# ReVersion (SIGGRAPH Asia, 2024) <!--  --> [](https://ziqihuangg.github.io/papers/2024SigAsia-ReVersion.pdf) [](https://arxiv.org/abs/2303.13495) [](https://ziqihuangg.github.io/projects/reversion.html) [](https://www.youtube.com/watch?v=pkal3yjyyKQ)  [](https://huggingface.co/spaces/Ziqi/ReVersion) This repository contains the implementation of the following paper: > **ReVersion: Diffusion-Based Relation Inversion from Images**<br> > [Ziqi Huang](https://ziqihuangg.github.io/)<sup>∗</sup>, [Tianxing Wu](https://tianxingwu.github.io/)<sup>∗</sup>, [Yuming Jiang](https://yumingj.github.io/), [Kelvin C.K. Chan](https://ckkelvinchan.github.io/), [Ziwei Liu](https://liuziwei7.github.io/)<br> From [MMLab@NTU](https://www.mmlab-ntu.com/) affiliated with S-Lab, Nanyang Technological University <!-- [[Paper](https://arxiv.org/abs/2303.13495)] | --> <!-- [[Project Page](https://ziqihuangg.github.io/projects/reversion.html)] | --> <!-- [[Video](https://www.youtube.com/watch?v=pkal3yjyyKQ)] | --> <!-- [[Dataset](https://drive.google.com/drive/folders/1FU1Ni-oDpxQCNYKo-ZLEfSGqO-j_Hw7X?usp=sharing)] --> <!-- [[Huggingface Demo](https://huggingface.co/spaces/Ziqi/ReVersion)] | --> ## :open_book: Overview  We propose a new task, **Relation Inversion**: Given a few exemplar images, where a relation co-exists in every image, we aim to find a relation prompt **\<R>** to capture this interaction, and apply the relation to new entities to synthesize new scenes. The above images are generated by our **ReVersion** framework. ## :heavy_check_mark: Updates - [12/2024] We are presenting ReVersion at [SIGGRAPH Asia 2024, Tokyo](https://asia.siggraph.org/2024/). Welcome to join our [presentation and discussion](https://asia.siggraph.org/2024/presentation/?id=papers_824&sess=sess105) on 3 December 2024. - [03/2024] We optimized the code implementation. You only need to save and load the relation prompt, without having to save or load the entire text-to-image model. - [08/2023] We released the [training code](https://github.com/ziqihuangg/ReVersion/tree/master#relation-inversion) for Relation Inversion. - [04/2023] We released the [ReVersion Benchmark](https://drive.google.com/drive/folders/1FU1Ni-oDpxQCNYKo-ZLEfSGqO-j_Hw7X?usp=sharing). - [04/2023] Integrated into [Hugging Face 🤗](https://huggingface.co/spaces) using [Gradio](https://github.com/gradio-app/gradio). Try out the online Demo: [](https://huggingface.co/spaces/Ziqi/ReVersion) - [03/2023] [Arxiv paper](https://arxiv.org/abs/2303.13495) available. - [03/2023] Pre-trained models with relation prompts released at [this link](https://drive.google.com/drive/folders/1apFk6TF3pGH00hHF1nO1S__tDlrcLQAh?usp=sharing). - [03/2023] [Project page](https://ziqihuangg.github.io/projects/reversion.html) and [video](https://www.youtube.com/watch?v=pkal3yjyyKQ) available. - [03/2023] Inference code released. ## :hammer: Installation 1. Clone Repo ```bash git clone https://github.com/ziqihuangg/ReVersion cd ReVersion ``` 2. Create Conda Environment and Install Dependencies ```bash conda create -n reversion conda activate reversion conda install python=3.8 pytorch=
Excerpt of 11,732 characters
Read on GitHub
15
5
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bd9b6e43fbb96f97, topic:stable-diffusion, topic:image-generation, readme:text-to-image