Name: 4x Normal RG0 BC1
Author: RunDevelopment

This collection contain my RG0 normal map upscaling models.

All models here are for upscaling *tangent-space* normal maps in RG0 format. RG0 means that the B channel is set to 0. These models will work not correctly if you give them images with non-zero B channel, so you either have to zero the B channel manually or use tool like chaiNNer to do it.

## DDS Compression

I made 3 versions: 
- Normal RG0 is for uncompressed normal map textures. Since it hasn't been trained on compression artifacts, it's highly sensitive to quantization artifacts and noise.
- Normal RG0 BC1 is for BC1-compressed DDS normal map textures.
- Normal RG0 BC7 is for BC7-compressed DDS normal map textures. This model sometimes produces images that aren't as sharp. In those cases, you can try the BC1 version to see whether it gives better results.

Normal Map Upscaling

To retain details while removing artifacts caused by dxt compression on textures

DEDXT

Removing compression artifacts from DXT1 compressed textures. This model was created to remove DXT1 compression artifacts from textures imported into the Source Engine. Compressed textures in the engine sometimes have a green-tint which this model also corrects. The data for this model contained a good mix of diffuse textures and normal maps which means this model is pretty good at removing compression from normals as well. Creating this model was a real learning experience for me and I hope someone finds a good use for it.

DXTDecompressor Source V3

This model is made for Source Engine textures. It tries to remove compression artifacts such as blockyness, discoloration, green tint. It does pretty well on a lot of things, realistic stuff as well, but it was mostly made to work on TF2 textures. It's made to keep as much detail as possible, without any unnecessary denoising/sharpening. Huge thanks to Twittman for assisting me along this journey.

DXTless SourceEngine

Gamecube and Wii textures Dumps.

It is designed as a faster alternative to the full size model, it requires much less Vram and is significantly faster.

HDCube Compact

Fine-tuned 4xFSDedither to upscale images from the game Riven, but should be better in general, particularly on ordered dithering. I adjusted the dataset to have a better variety of dithering parameters, and turned up the HFEN and pixel loss to get better details and color restoration with less noise.

FSDedither Riven

Category: Fabric/Cloth
Purpose: Fabric

This model set upscales fabric or cloth textures (works on cats too!). The Alt model is just an earlier iteration version. It may work better on some images.The images need to be minimally compressed or passed through a decompression model first. It works with DDS compression though.

Fabric

Fabric-Alt

Purpose: Anime PSP games, Fate Extra

This model was trained as a favor to Demon and the Fate Extra community. It leaves a nice grain on the images and upscales lines and details accurately without looking odd. This model works on most anime-style PSP games. Enjoy! It works best on content with dithering and quantization. NOTICE: I have included both NCNN and ONNX models to make upscaling easier if you rely on either of these. For NCNN, there's two versions. One is FP16 and the other is FP32. FP16 works best on RTX GPUs. Choose FP32 if in doubt about compatibility, or if FP16 doesn't work for you. To use ONNX, download chaiNNer and upscale through there with the ONNX nodes.

FatePlus-lite

Images from the Fate/Extra games. Works better on the newer ones.

Just a model I trained quickly to test traiNNer-redux and see what I could do with OTF. Works well enough

FatePlus Compact

This model is intended to mainly handle PS2 compression and a mixture of Realistic and cartoonish textures, it's not meant to be used for very low resolution textures such as item icons.

GameAI 1.0

GameAI 2.0

Category: Foliage/Ground
Purpose: Upscales ground textures

Ground

Purpose: Gamecube and Wii textures.

Gamecube and Wii textures (mainly DXT and 8bit color compression). Is good for preserving fine details without affecting the original style too much, it is not suitable for pixel art, small icons and text under 16 pixel.

Pretrained model: 4x_NMKD Siax

HDCube

Gamecube and Wii textures Dumps.

https://github.com/Venomalia/HDcube/tree/main/v2

HDCube2

Purpose: Gamecube and Wii textures.
Pretrained: 4x_HDcube2

It can be used for all image formats supported by Gamecube and Wii hardware and can remove its typical artifacts like CMPR Block Compression (DXT1 algorithm, also known as BC1), color palette errors, color reduction up to 8bit color depth and 1bit alpha depth.

HDCube3

A 4x upscaler for uncompressed normal maps with a zeroed-out B channel. The input is required to have no alpha and constant-zero blue channel. The model can handle some light compression artifacts but has trouble with quantization artifacts. The output normals will also have a constant-zero B channel. Use external software or image editing plugins to properly normalize the generated normals and generate the Z component (if necessary). E.g. chaiNNer can do this with Normalize Normal Map node. Do not rely on this network producing unit vectors.


More information: https://github.com/RunDevelopment/ESRGAN-models/blob/main/normals/README.md

Normal RG0

A 4x upscaler for BC1-compressed normal maps with a zeroed-out B channel. The output normals will also have a constant-zero B channel. Use external software or image editing plugins to properly normalize the generated normals and generate the Z component (if necessary). E.g. chaiNNer can do this with Normalize Normal Map node. Do not rely on this network producing unit vectors. 

**Dataset transformation:** \
The LR have been compressed with various BC1 compression settings (dithering, weighting) using Texconv version 2021.11.8.1. Since the contents of the B channel influence the R and G channels during compression, the LR were given a B channel that was either the Z component of the normal, a random constant color, or a random texture (usually the G channel of the associated albedo) before compression. The LR + B channel was then compressed and the resulting BC1-compressed DDS was converted back into a PNG and had its B channel zeroed out.

More information: https://github.com/RunDevelopment/ESRGAN-models/blob/main/normals/README.md

Normal RG0 BC1

A 4x upscaler for BC7-compressed normal maps with a zeroed-out B channel and no alpha. The input is required to have no alpha and constant-zero blue channel. BC7-compressed images with an alpha channel should be handled by the BC1 model instead. This is because BC7 achieves very different quality for images with and without an alpha channel. The output normals will also have a constant-zero B channel. The output normals will also have a constant-zero B channel. Use external software or image editing plugins to properly normalize the generated normals and generate the Z component (if necessary). E.g. chaiNNer can do this with Normalize Normal Map node. Do not rely on this network producing unit vectors. 

**Dataset transformation:** \
The LR have been compressed using Texconv version 2021.11.8.1. Since the contents of the B channel influence the R and G channels during compression, the LR were given a B channel that was either the Z component of the normal, a random constant color, or a random texture (usually the G channel of the associated albedo) before compression. The LR + B channel was then compressed and the resulting BC7-compressed DDS was converted back into a PNG and had its B channel zeroed out.

More information: https://github.com/RunDevelopment/ESRGAN-models/blob/main/normals/README.md

Normal RG0 BC7

PBRify Github: https://github.com/Kim2091/PBRify_Remix

Release Link: https://github.com/Kim2091/Kim2091-Models/releases/tag/4x-PBRify_RPLKSRd_V3

This update brings a new upscaling model, 4x-PBRify_RPLKSRd_V3. This model is roughly 8x faster than the current DAT2 model, while being *higher quality*. It produces far more natural detail, resolves lines and edges more smoothly, and cleans up compression artifacts better.

As a result of those improvements, PBR is also much improved. It tends to be clearer with less defined artifacts. 

However, this model is currently **only compatible with ComfyUI**. chaiNNer has not yet been updated to support this architecture.

[More Comparisons](https://imgsli.com/Mjk5NjQ5)

4x-PBRify_RPLKSRd_V3

Project page: https://github.com/Kim2091/PBRify_Remix

Yet another model in the PBRify_Remix series. This is a new upscaler to replace the previous 4x-PBRify_UpscalerSIR-M_V2 model.

This model far exceeds the quality of the previous, with far more natural detail generation and better reconstruction of lines and edges.

Comparison: https://slow.pics/c/DCjlXPGb

4x-PBRify_UpscalerDAT2_V1

This is part of my [PBRify_Remix](<https://github.com/Kim2091/PBRify_Remix>) project. This is a much more capable model based on SwinIR Medium, which should strike a balance between capacity for learning + inference speed. It appears to have done so :)

### Replaced by 4x-PBRify_UpscalerDAT2_V1

4x-PBRify_UpscalerSIR-M_V2

This is part of a larger model set, PBRify_Remix. PBRify_Remix is an easy way to upscale and generate PBR textures using existing low quality textures. The dataset consists of ethically sourced textures from websites like ambientCG and Polyhaven, which sets it apart from most other models.

It's intended for use with RTX Remix (hence the name) but it'll work for other things as well.

4x-PBRify_UpscalerSPANV4

This model was made to upscale realistic low-res textures that are compressed by either JPEG or BC1. From my testing, this works rather well on realistic GameCube textures such as the ones from Shrek Extra Large and the board textures from Mario Party 4. This model could also work on some real life images, especially the ones that are taken outdoors.

RealisticRescaler

## 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)

4xTextures_GTAV_rgt-s_dither

Purpose: Game textures/Art

This model upscales artwork for the game Volfoss (2001). The model peaked in quality very quickly. The NR model removes most noise, but has the downside of removing transparent portions. Use the main model in most cases.

VolArt

A 4x upscaler for BC1-compressed wood textures. The model was trained on wood planks, wood stems, and a bit of tree bark. It performs reasonably well on woody textures and produces sharp outputs. However, it also tends to slightly shift the hue of the image, so results might appear slightly more red.

More information: https://github.com/RunDevelopment/ESRGAN-models/blob/main/wood/README.md

Architecture	ESRGAN
Scale	4x
Size	64nf23nb
Color Mode	RGB
License	CC0-1.0 Private use Commercial use Distribution Modifications No Liability & Warranty Disclaimer
Date	2022-04-02
Dataset	Custom. See description.
Dataset size	577
Training iterations	100000
Training epochs	89
Training batch size	8
Training HR size	128
Training OTF	No

Normal RG0 BC1

Collections that include this model

Similar Models