---
language:
- ru
- en
tags:
- PyTorch
thumbnail: "https://github.com/ai-forever/MoVQGAN/"
---
# SBER-MoVQGAN

SBER-MoVQGAN is a new SOTA model in the image reconstruction problem. 
This model is based on code from the [VQGAN](https://github.com/CompVis/taming-transformers) repository and modifications from the original [MoVQGAN](https://arxiv.org/pdf/2209.09002.pdf) paper.

Code for using SBER-MoVQGAN you can obtain in our [repo](https://github.com/ai-forever/MoVQGAN/tree/main).

## Models
The following table compares the 3 versions of the model SBER-MoVQGAN on the Imagenet dataset in terms of FID, SSIM and PSNR metrics.
A more detailed description of the experiments and a comparison with other models can be found in the [Habr](https://habr.com/ru/companies/sberbank/articles/740624/) post.

|Model|Train steps|FID|SSIM|PSNR|
|:----|:----|:----|:----|:----|
| f=8, [SBER-MoVQGAN 67M]((https://huggingface.co/ai-forever/MoVQGAN/resolve/main/movqgan_67M.ckpt)) | 2M | 0,96 | 0,7249 | 26,45 |
| f=8, [SBER-MoVQGAN 102M](https://huggingface.co/ai-forever/MoVQGAN/resolve/main/movqgan_102M.ckpt)| 2360k | 0,78 | 0,7373 | 26,89 |
| f=8, [SBER-MoVQGAN 270M](https://huggingface.co/ai-forever/MoVQGAN/resolve/main/movqgan_270M.ckpt) | 1330k | **0,69** | **0,7411** | **27,04** |