https://github.com/singlezombie/afldm
[CVPR 2025] Alias-free Latent Diffusion Models official implementation
https://github.com/singlezombie/afldm
artificial-intelligence computer-vision
Last synced: over 1 year ago
JSON representation
[CVPR 2025] Alias-free Latent Diffusion Models official implementation
- Host: GitHub
- URL: https://github.com/singlezombie/afldm
- Owner: SingleZombie
- License: other
- Created: 2025-03-12T13:05:18.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-12T13:17:50.000Z (over 1 year ago)
- Last Synced: 2025-03-12T14:22:23.615Z (over 1 year ago)
- Topics: artificial-intelligence, computer-vision
- Language: Python
- Homepage: https://zhouyifan.net/AF-LDM-Page/
- Size: 3.48 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
[CVPR 2025] Alias-free Latent Diffusion Models
Yifan Zhou1
Zeqi Xiao1
Shuai Yang2
Xingang Pan1
1S-Lab, Nanyang Technological University,
2Wangxuan Institute of Computer Technology, Peking University
Project Page |
Paper
Offical PyTorch implementation of Alias-free latent diffusion models.
## Motivation
https://github.com/user-attachments/assets/4fcd0c0f-4c0f-48a9-97dc-e5dcab9dd578
We found the VAE and denoising network in LDM are not equivariant to fractional shifts. We propose an alias-free framework to improve the fractional shift equivariance of LDM. We demonstrate the effectiveness of our method in various applications, including video editing, frame interpolation, super-resolution and normal estimation.
## TODO
- [ ] Chinese/English blog posts
- [ ] Refine documents
- [ ] Training scripts
## Update
* \[03/2025\]: Repository created.
## Installation
1. Clone the repository. (Don't forget --recursive. Otherwise, please run git submodule update --init --recursive)
```shell
git clone git@github.com:SingleZombie/AFLDM.git --recursive
cd AFLDM
pip install -e .
```
2. Install PyTorch in your Python environment.
3. Install pip libraries.
```shell
pip install -r requirements.txt
```
## Inference
All the detailed commands are shown inside `.sh` files.
### Unconditional Generation Shift
```shell
bash shift_ldm_ffhq.sh
```
### Video Editing
Due to the limitation of our computation resource, the finetuned alias-free Stable Diffusion has a poor generation capacity. It can only perform simple editing.
```shell
bash video_editing.sh
```
### Image Interpolation
```shell
bash image_interpolation.sh
```
### Super-resolution Shift
This is not a blind SR. The degradation function is fixed.
```shell
bash shift_ldm_sr.sh
```
### Normal Esitmation Shift
```shell
bash shift_normal_estimation.sh
```
## Citation
```
@inproceedings{zhou2025afldm,
title={Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space},
author={Zhou, Yifan and Xiao, Zeqi and Yang, Shuai and Pan, Xingang },
booktitle = {CVPR},
year = {2025},
}
```
## Acknowledgements
* [Diffusers](https://github.com/huggingface/diffusers): Our project is bulit on diffusers.
* [GMFlow](https://github.com/haofeixu/gmflow): Our flow estimator.
* [StyleGAN3](https://github.com/NVlabs/stylegan3): For sharing alias-free module implementation.
* [Alias-Free Convnets](https://github.com/hmichaeli/alias_free_convnets): For sharing alias-free module implementation.
* [I2SB](https://github.com/NVlabs/I2SB): For sharing SR implementation.
* [StableNormal](https://github.com/Stable-X/StableNormal): For sharing normal estimation dataset.