Halo Removal + edge removal. This model softens edges without blurring other parts of the image.

Comparison and use case: https://imgsli.com/MjgxMDU

DeEdge

This is a 1x model for removing halos in animation. I was training this a while back and considered it a failed project, but I recently found it useful on a few things I was working on, so I decided to release it. I don't remember any details regarding how it was trained.

Dehalo_v1_Compact

This model is far from perfect, but it does a decent job on removing dot crawl and dehalo\deblock old anime at fast rate without removing many details. chaining it with models like 2x-anifilm-compact or 2xLD-ANIME or 2x_AnimeClassics_UltraLite_510K will give good results i think.

Epsilon-one compact

## Ani4K v2  

 Ani4K v2, as the successor to the original Ani4K, retains its predecessor's fantastic detail retention, depth of field preservation and faithfulness to the original source. As the name suggests, the model is targeted at modern anime, ranging from high-quality Bluray to crappy WEB releases, for upscaling either to 2K or 4K.

An **UltraCompact** version of the model is available on the [Github release](https://github.com/Sirosky/Upscale-Hub/releases/tag/Ani4K-v2). The UltraCompact version is faster, without a perceptual hit to quality in most cases.

📌 [More comparisons](https://slow.pics/c/1HykdyT5)

****

**FAQ**

- *How does v2 differ from v1?* I'm so glad you asked! A shortcoming of the v1 models is that the model really struggled on sources which were poorly mastered. This is unfortunately still very common even with modern anime. v2 is far more capable of dealing with such sources. 
- *How does Ani4K v2 differ from JaNai v3? Which one should I pick?* JaNai v3 is a fantastic model, and shares many of the fundamental training objectives behind Ani4K (DOF preservation, faithfulness, etc.). I'd say that the primary difference is one of training philosophy-- JaNai seeks to render the source as if it was originally mastered in 4K, whereas Ani4K seeks to produce an upscale that is as close as possible to the source (while cleaning up any issues). Long story short, test both models and see which you prefer.
- *What model versions are there?* Ani4K comes in Compact and UltraCompact flavors. Compact is of course a standard option. UltraCompact provides a noticeable performance uplift, without too much impact on quality. I ultimately did not train a SuperUltraCompact variant as I felt the hit to the model quality was far too significant.

Ani4VK v2 Compact

## AniSD Suite (15 models)

**Scale:** 2x (1x for AniSD DB)  
**Architecture:** SPAN / Compact / SwinIR Small / CRAFT / DAT2  / RPLKSR

**Dataset:** Anime frames. Credits to @.kuronoe. and @pwnsweet (EVA dataset) for their contributions to the dataset!  
**Dataset Size:** ~7,000 - ~13,000  

AniSD is a suite of 15 (as of time of writing) specialized SISR models trained to restore and upscale standard definition digital anime from ~2000s and onwards, including both both WEB and DVD releases. Faithfulness to the source and natural-looking output are the guiding principles behind the training of the AniSD models. This means avoiding oversharpened output (which can look especially absurd on standard definition sources), minimizing upscaling artifacts, retaining the natural detail of the source and of course, fixing the standard range of issues found in many DVD/WEB release (chroma issues, compression, haloing/ringing, blur, dotcrawl, banding etc.). Refer to the infographic above for a quick breakdown of the available models, and refer to the [Github release](https://github.com/Sirosky/Upscale-Hub/releases/tag/AniSD-RealPLKSR) for further information.

AniSD Suite (Multiple Models)

2x general purpose anime upscaler, with a focus on cleaning up scuffed sources while enhancing texture detail. While the model was trained on DVDs, it still works well on modern anime. The model is trained to deal with noise, compression artifacts, blur, bleeding, haloing and scuffed line art. Apparently, it also learned to deal with some dotcrawl.

AniScale

upscaling old anime. help to denoise and find lines and dehalo

BIGOLDIES

[Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021)](https://github.com/cszn/BSRGAN)

BSRGANx2

Purpose: Digital Animation

Meant as a versatile model for upscaling high detail digital anime and cartoons. Has debanding, MPEG-2 correction, and halo reduction. Trained to handle both 4:3 and 16:9 DVD material with equal efficacy. Will retain a lot of textures except for the really high freq stuff.

Digitoon Lite

A 2x Compact anime upscale model that handles AVC (h264) degradation. Applied h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling on musl's HFA2k dataset with Kim's dataset destroyer.

2xHFA2kAVCCompact

A 2x EDSR M anime upscale model that handles AVC (h264) degradation. Applied h264 crf 20-28 degradation and bicubic, bilinear, box and lanczos downsampling on musl's HFA2k dataset with Kim's dataset destroyer.

2xHFA2kAVCEDSR_M

The second released community trained model on the OmniSR network. Trained with multiscale discriminator to fix decreased output brightness occuring with OmniSR. 2x anime upscale that handles AVC (h264) compression since h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling has been applied on musl's HFA2k dataset with Kim's dataset destroyer.

2xHFA2kAVCOmniSR

2x SRFormer_light anime upscale model that handles AVC (h264) compression since h264 crf 20-28 degradation together with bicubic, bilinear, box and lanczos downsampling has been applied on musl's HFA2k dataset with Kim's dataset destroyer for training.


If you want to run this model with chaiNNer (or another application) you need to use the onnx files with an onnx upscale node. All onnx conversions can be found in the [onnx folder on my repo](https://github.com/Phhofm/models/tree/main/2xHFA2kAVCSRFormer_light/onnx).

Example 1: https://imgsli.com/MTkxMTQz

Example 2: https://imgsli.com/MTkxMTQ0

2xHFA2kAVCSRFormer_light

I trained Skr's great LD-Anime model on compact architecture. It upscales while fixing numerous video problems, including: noise/grain, compression artifacts, rainbows, dot crawl, halos and color bleed. This compact version may look slightly worse than Skr's original model, but runs significantly faster and also retains the correct colors better than the original model did.

LD-Anime Compact

Purpose: Denoise/Dehalo

Denoise, dehalo, derainbow old anime

LD-Anime_Skr v1.0

Purpose: Upscale text in very low quality to normal quality.

The upscale model is specifically designed to enhance lower-quality text images, improving their clarity and readability by upscaling them by 2x. It excels at processing moderately sized text, effectively transforming it into high-quality, legible scans. However, the model may encounter challenges when dealing with very small text, as its performance is optimized for text of a certain minimum size. For best results, input images should contain text that is not excessively small.

Text2HD v.1

Category: VHS Tapes
Purpose: VHS

VHS captures of Film material, but may work on VHS recorded native SD-TV material as well. Also useable for cleaned up source material

VHS upscale and denoise Film

Purpose: VHS Restoration

An advanced VHS recording model designed to enhance video quality by reducing artifacts such as haloing, ghosting, and noise patterns. Optimized primarily for PAL resolution (NTSC might work good as well).

VHS2HD

[SwinIR: Image Restoration Using Swin Transformer](https://github.com/JingyunLiang/SwinIR)


Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14~0.45dB, while the total number of parameters can be reduced by up to 67%.

SwinIR-M-x2 (classicalSR-DF2K-s64w8)

SwinIR-M-x2 (classicalSR-DIV2K-s64w8)

SwinIR-M-x2 (lightweightSR-DIV2K-s64w8)

SwinIR-M-x2-GAN (realSR-BSRGAN-DFO-s64w8)

[Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) aims at developing Practical Algorithms for General Image/Video Restoration.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data.

RealESRGAN_x2Plus

DeIndeo

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)

Architecture	RealPLKSR
Scale	2x
Color Mode	RGB
License	CC-BY-SA-4.0 Private use Commercial use Distribution Modifications Credit required Same License State Changes No Liability & Warranty Disclaimer
Date	2024-08-27
Dataset	Movies and private films
Dataset size	6019
Training iterations	385000
Training batch size	8
Training OTF	No

VHS2HD

Similar Models