Many preview images on this site are currently broken due to their original hosts being indefinitely offline. Work is underway to recover the affected images and rehost them somewhere reliable.

Tags

Not in edit mode!

(This will go through all models and add tags if necessary to reflect current tag implications.)

Subject

AI Generated (0)

Images or videos rendered with tools such as Stable Diffusion

Anime (0)

Image or video of anime or anime-style artwork.

Cartoon (0)

Image or video of western cartoon or artwork in a similar style.

CGI (0)

Computer Generated Imagery (CGI). These are images or videos that have been rendered in software such as Blender. A good example would be the movie "Toy Story"

Faces (0)

Image or video of faces. This can be photograph or artwork.

Game Screenshots (0)

Images (screenshots) taken of video games.

Game Textures (0)

Textures used in video games or other 3D applications. These textures are typically diffuse/albedo maps, but other types of textures (such as normal maps) are also included.

Manga (0)

Image of manga pages or manga-style artwork.

Pixel Art (0)

Pixel art. This includes things such as retro pixel artwork (think SNES games).

Realistic (0)

Image or video of realistic looking imagery. E.g. images recorded with camera.

Text (0)

Image or video of text.

Video Frame (0)

Images of individual video frames.

Purpose

Anti-aliasing (0)

The model smooths aliasing artifacts (also called jaggies).

Colorization (0)

The model colorizes grayscale and/or black-and-white images.

Compression Removal (0)

The model is capable of removing compression. This can be any type of compression, such as JPEG or H264.

DDS (0)

The model is able to remove DDS block compression artifacts.

Models with this tag may only support specific compression methods and/or settings (e.g. BC1/DTX1, BC7).

Debanding (0)

The removes banding artifacts caused by color quantization. Such artifacts and frequently be observed in GIF images.

Deblur (0)

The model tries to remove blur from the input.

Dedither (0)

The model removes dithering artifacts from the input.

Dehalftone (0)

The model removes halftone patterns from the input. This is typically on printed media, such as magazines or album covers.

Dehalo (0)

The model removes haloing and color bleeding from the input.

Denoise (0)

The model removes noise from the input.

Models with this tag may only work with specific kinds of noise.

General Upscaler (0)

The model can upscale any subject.

General purpose models achieve good results across a wide range of inputs. However, models that specialize in the subject of a specific image (e.g. anime, faces, text, etc.) will typically achieve better results than general purpose models.

Inpainting (0)

The model fills in selected parts of an image.

JPEG (0)

The model is able to remove JPEG compression artifacts.

Models with this tag may only support specific JPEG compression settings (e.g. quality between 80% and 100%).

Pretrained (0)

The model is intended to be used to train new models.

Research (0)

The model is the result of a research paper. The paper or GitHub repo is typically linked in the description.

Restoration (0)

The model restores images or video frames through compression removal, artifact clean up, or otherwise.

Texture Generation (0)

The model generates textures from other textures. E.g. a model could generate a normal map from a diffuse texture.

ArchitectureEdit Architectures

CAIN (0)

No description

CAIN YUV (0)

No description

Compact (0)

No description

CRAFT (0)

No description

CUGAN (0)

No description

DAT (0)

No description

DCTLSA (0)

No description

DITN (0)

No description

EDSR (0)

No description

ESRGAN (0)

No description

ESRGAN+ (0)

No description

GRL (0)

No description

HAT (0)

No description

LUDVAE (0)

No description

OmniSR (0)

No description

Real-CUGAN (0)

No description

RGT (0)

No description

RIFE (0)

No description

SOFVSR (0)

No description

SPAN (0)

No description

SPSR (0)

No description

SRFormer (0)

No description

SRResNet (0)

No description

Swift-SRGAN (0)

No description

SwinIR (0)

No description

ATD (0)

No description

DRCT (0)

No description

RealPLKSR (0)

No description

RealPLKSR_dysample (0)

No description

HMA (0)

No description

MoSR (0)

No description

RCAN (0)

No description

TSCUNet (0)

No description

Platform

PyTorch (0)

The model has PyTorch models (.pth/.pt) to download.

PyTorch Compatible (0)

The either has PyTorch models to download or can be converted into a PyTorch model.

ONNX (0)

The model has ONNX models (.onnx) to download.

ONNX Compatible (0)

The either has ONNX models to download or can be converted into an ONNX model.

NCNN (0)

The model has NCNN models (.bin+.param) to download.

NCNN Compatible (0)

The either has NCNN models to download or can be converted into an NCNN model.

Scale

1x (0)

No description

2x (0)

No description

3x (0)

No description

4x (0)

No description

8x (0)

No description

16x (0)

No description

Input type

Audio (0)

No description

Image (0)

No description

Video (0)

No description

Color

Grayscale (0)

The model upscales grayscale images. A typical example for grayscale models are models that upscale the alpha channel of images.

RGB (0)

The model upscales images without transparency. Some applications (e.g. chaiNNer and CupScale) can still upscale images with transparency using this model.

RGBA (0)

The model upscales images with transparency.

Grayscale→RGB (0)

The model colorizes grayscale images to RGB.

License

Credit (0)

Crediting the author is required when sharing the model or derivative works (e.g. model interpolations).

Simply using the model to upscale images is typically okay, and no credit is required for upscaled images.

Commercial (0)

The model may be included and used in commercial products.

Modifications (0)

The author allows that this model may be used to create derivative works (e.g. model interpolations).

Same license (0)

The author requires that derivative works have the same license or a compatible license as the model. Derivative works include model interpolations and using it a pretrained model.

Unknown License (0)

The model either has no license or is licensed under a custom or infrequently used license.

Helpers

Needs description (0)

The model has no description.

Needs tags (0)

The model has no tags.

Invalid date (0)

The model has no date or its date is invalid.

Invalid scale (0)

The scale of the model is not valid.

Invalid channels (0)

The number of input or output channels of the model is not valid.

Dataset

Realistic (0)

Realistic dataset

Anime (0)

Anime dataset

Manga (0)

Manga dataset

Game Textures (0)

Game textures dataset