Skip to content
ModelListedExternal
Download

2xHFA2kAVCSRFormer Light

Name: 2xHFA2kAVCSRFormerlight Author: Philip Hofmann Release Date: 11.07.2023 License: CC BY 4.0 Network: SRFormerlight Scale: 2 Purpose: 2x anime upscaling model that handles AVC (h264) compression Iterations:...

Sourcehuggingface.co/Phips/2xHFA2kAVCSRFormer_light/tree/6a00c4ad0701482c70e7a892b413f57ffed3b903
KindOtherVersion2x HFA2k AVCSRFormer lightCgrade

Model source

Kind
Other
File size
18.3 MB
Version
v2x HFA2k AVCSRFormer light
Updated
Oct 26, 2026
Source
Hugging Face

Source description

Link to Github Release

2xHFA2kAVCSRFormer_light

Name: 2xHFA2kAVCSRFormer_light
Author: Philip Hofmann
Release Date: 11.07.2023
License: CC BY 4.0
Network: SRFormer_light
Scale: 2
Purpose: 2x anime upscaling model that handles AVC (h264) compression
Iterations: 140000
batch_size: 2-4
HR_size: 128-192
Dataset: HFA2k_h264
Number of train images: 2568
OTF Training: No
Pretrained_Model_G: SRFormerLight_SRx2_DIV2K.pth

Description: 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.

Example 1: https://imgsli.com/MTkxMTQz
Example 2: https://imgsli.com/MTkxMTQ0

Example1
Example2

Sources

1 source
Hugging FacePrimaryVersion 6a00c4ad0701482c70e7a892b413f57ffed3b903
huggingface.co/Phips/2xHFA2kAVCSRFormer_light/tree/6a00c4ad0701482c70e7a892b413f57ffed3b903

Verified Oct 26

Model artifacts

1 artifact

2xHFA2kAVCSRFormer_light.safetensors

safetensors · 18.3 MB · SHA-256 fd423c929806…1ba3 · Hugging Face

Download file

Source excerpts

2 excerpts
ReadmeAug 8huggingface.co/Phips/2xHFA2kAVCSRFormer_light

--- 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/2xHFA2kAVCSRFormer_light) # 2xHFA2kAVCSRFormer_light Name: 2xHFA2kAVCSRFormer_light Author: Philip Hofmann Release Date: 11.07.2023 License: CC BY 4.0 Network: SRFormer_light Scale: 2 Purpose: 2x anime upscaling model that handles AVC (h264) compression Iterations: 140000 batch_size: 2-4 HR_size: 128-192 Dataset: HFA2k_h264 Number of train images: 2568 OTF Training: No Pretrained_Model_G: SRFormerLight_SRx2_DIV2K.pth Description: 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](https://github.com/Phhofm/models/tree/main/2xHFA2kAVCSRFormer_light/onnx) on my repo. Example 1: https://imgsli.com/MTkxMTQz Example 2: https://imgsli.com/MTkxMTQ0 ![Example1](https://github.com/Phhofm/models/assets/14755670/d790378e-3a06-4b3c-8d74-39378e82c19a) ![Example2](https://github.com/Phhofm/models/assets/14755670/105b16c4-5041-48d5-a981-b2317bf79d4a)

NoteAug 8huggingface.co/Phips/2xHFA2kAVCSRFormer_light

Source context: 0 downloads · 0 likes · Pipeline image-to-image · Repo Phips/2xHFA2kAVCSRFormer_light