---
license: cc-by-4.0
pipeline_tag: image-to-image
tags:
- pytorch
- super-resolution
---

[Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xTextures_GTAV_rgt-s_dither)

# 4xTextures_GTAV_rgt-s_dither

**Scale:** 4  
**Architecture:** [RGT](https://github.com/zhengchen1999/RGT)  
**Architecture Option:** RGT-S  

**Author:** Philip Hofmann  
**License:** CC-BY-0.4  
**Purpose:** Restoration  
**Subject:** Game Textures  
**Input Type:** Images  
**Release Date:** 08.05.2024  

**Dataset:** [GTAV_512_Textures](https://discord.com/channels/547949405949657098/905446120333930566/1132367991808466975)  
**Dataset Size:** 7061  
**OTF (on the fly augmentations):** No  
**Pretrained Model:** 4xTextures_GTAV_rgt-s  
**Iterations:** 128'000  
**Batch Size:** 6,4  
**GT Size:** 128,256  

**Description:** A model to upscale game textures, trained on GTAV Textures, handles jpg compression down to 80 and was trained with dithering. Basically the previous 4xTextures_GTAV_rgt-s model but extended to handle dithering.

**Showcase:**
[Slow Pics 25 Examples](https://slow.pics/s/EW7Ifiuw)

![Example1](https://github.com/Phhofm/models/assets/14755670/e0b8c55b-8bcb-4055-9e5a-63bef996059c)
![Example2](https://github.com/Phhofm/models/assets/14755670/ec25ee27-a199-467f-9d60-a5aaad6ca59f)
![Example3](https://github.com/Phhofm/models/assets/14755670/a546b593-0adc-4363-b4f6-eb8c57b0d606)
![Example4](https://github.com/Phhofm/models/assets/14755670/d925d5ff-872d-4e53-b1f8-52ca17b15e46)
![Example5](https://github.com/Phhofm/models/assets/14755670/29de9d90-9d95-41a6-9f31-7d980ad2428e)
![Example6](https://github.com/Phhofm/models/assets/14755670/7ba95476-f689-4d20-95e1-30a5d8690333)
![Example7](https://github.com/Phhofm/models/assets/14755670/99b9aee1-cd84-45e9-90fb-edec802f1b7d)
![Example8](https://github.com/Phhofm/models/assets/14755670/0dfa8687-441d-4c17-9611-c8355b4e91ad)
![Example9](https://github.com/Phhofm/models/assets/14755670/a4722d99-4365-4532-92c1-54603bd514a3)
![Example10](https://github.com/Phhofm/models/assets/14755670/08958df9-aaa8-46e3-8af1-a2c21f16bb50)
![Example11](https://github.com/Phhofm/models/assets/14755670/efbfbeb1-efa0-4ff2-9501-2a4232fa64b4)
![Example12](https://github.com/Phhofm/models/assets/14755670/74973832-a3cc-4db1-95b0-8041ac1d79f6)
![Example13](https://github.com/Phhofm/models/assets/14755670/eef93549-e69d-4032-bcdf-7217ce522f8a)
![Example14](https://github.com/Phhofm/models/assets/14755670/ba5bb6a2-1427-48af-a06d-00c8c55b6837)
![Example15](https://github.com/Phhofm/models/assets/14755670/0c82dee2-316f-4eb7-b223-79f7c4e420c0)
![Example16](https://github.com/Phhofm/models/assets/14755670/b8820f32-8f9a-4cb3-91d0-f672526107af)
![Example17](https://github.com/Phhofm/models/assets/14755670/36cb8086-f19b-4759-90b2-76a12e0e0085)
![Example18](https://github.com/Phhofm/models/assets/14755670/a7519b43-e6c1-48fc-b173-464bee880083)
![Example19](https://github.com/Phhofm/models/assets/14755670/9db0f7f6-259d-4534-84dc-f5c738bb4b47)
![Example20](https://github.com/Phhofm/models/assets/14755670/41750090-b7e9-4b14-a01d-4b7bc58f649b)
![Example21](https://github.com/Phhofm/models/assets/14755670/15d9de9e-3d8e-453d-ad91-93aa7b6eb422)
![Example22](https://github.com/Phhofm/models/assets/14755670/166015fc-b21b-4f19-98b2-d9495b08deb0)
![Example23](https://github.com/Phhofm/models/assets/14755670/bae91325-a4b7-4097-a04c-295d0fbb9d7c)
![Example24](https://github.com/Phhofm/models/assets/14755670/0447b40e-b442-4cdb-8094-50009740d705)
![Example25](https://github.com/Phhofm/models/assets/14755670/dcc1c19a-4c63-43e1-8704-5545b0641b2c)
![Example26](https://github.com/Phhofm/models/assets/14755670/094c594d-b68e-44d2-ab1f-9a387ef4ace2)
![Example27](https://github.com/Phhofm/models/assets/14755670/76b5271f-4e91-42b9-b0a1-6bf5389aa282)