hugglyberry/upscale-and-refine-models
By hugglyberry · ↓ 0 · ♥ 0 · Updated 2026-03-13
What's in this repo
This page lists the files in hugglyberry/upscale-and-refine-models, including 1x-aniscale2-refiner.onnx, 1x-artclarity.onnx, 1x-ghibli-grain.onnx and more.
- 53 ONNX models (.onnx files)
- 73 files, including 53 .onnx, 15 .data, 2 .wasm, 1 .md
- Last updated 2026-03-13
ONNX files
| File | Size | Download |
|---|---|---|
| 1x-aniscale2-refiner.onnx | — | Download |
| 1x-artclarity.onnx | — | Download |
| 1x-ghibli-grain.onnx | — | Download |
| 1x-hurrdeblur-superultracompact.onnx | — | Download |
| 1xDeH264_realplksr.onnx | — | Download |
| 1xDeJPG_realplksr_otf.onnx | — | Download |
| 1xDeNoise_realplksr_otf.onnx | — | Download |
| 4xNomosWebPhoto_atd.onnx | — | Download |
| BiRefNet-lite-fp16.onnx | — | Download |
| NAFNet-GoPro-width64.onnx | — | Download |
Showing 10 of 53 .onnx files — see the full file list on the right.
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
license: other license_name: mixed license_link: LICENSE
Upscale and Refine Models
A curated collection of ONNX models for image upscaling, denoising, deblurring, colorization, segmentation, and other image restoration tasks. All models are in ONNX format for easy cross-platform inference.
Models
Upscaling
| Model | Scale | Description |
|---|---|---|
4xNomosWebPhoto_atd |
4x | High-quality photo upscaler |
SwinIR-4x-GAN |
4x | SwinIR GAN-based upscaler |
SPAN-4x |
4x | Lightweight efficient upscaler |
realcugan-2x-* |
2x | Real-CUGAN variants (conservative, no-denoise, denoise 1x/2x/3x) |
realcugan-3x-* |
3x | Real-CUGAN variants (conservative, denoise 3x) |
realcugan-4x-* |
4x | Real-CUGAN variants (conservative, no-denoise, denoise 3x) |
realesrgan-general-* |
4x | Real-ESRGAN for general photos (fast / plus) |
realesrgan-anime-* |
4x | Real-ESRGAN for anime images (fast / plus) |
Denoising & Artifact Removal
| Model | Description |
|---|---|
1xDeNoise_realplksr_otf |
General denoising |
1xDeJPG_realplksr_otf |
JPEG artifact removal |
1xDeH264_realplksr |
H.264 compression artifact removal |
SCUNet-PSNR |
Blind denoising (PSNR-oriented) |
SCUNet-GAN |
Blind denoising (GAN-oriented, perceptual) |
dncnn-color-blind |
Blind color image denoising |
NAFNet-SIDD-width64 |
Real-world denoising |
Deblurring
| Model | Description |
|---|---|
1x-hurrdeblur-superultracompact |
Lightweight deblurring |
NAFNet-GoPro-width64 |
Motion deblurring (GoPro) |
NAFNet-REDS-width64 |
Motion deblurring (REDS) |
maxim-deblurring |
MAXIM deblurring |
maxim-deblurring-reds |
MAXIM deblurring (REDS) |
maxim-deblurring-realblur-j |
MAXIM deblurring (RealBlur-J) |
maxim-deblurring-realblur-r |
MAXIM deblurring (RealBlur-R) |
Image Enhancement & Restoration
| Model | Description |
|---|---|
maxim-enhancement |
Low-light enhancement |
maxim-retouching |
Photo retouching |
maxim-dehazing-indoor |
Indoor dehazing |
maxim-dehazing-outdoor |
Outdoor dehazing |
maxim-deraining |
Deraining |
maxim-deraining-raindrop |
Raindrop removal |
maxim-denoising |
MAXIM denoising |
Refinement
| Model | Description |
|---|---|
1x-aniscale2-refiner |
Anime refinement |
1x-artclarity |
Art clarity enhancement |
1x-ghibli-grain |
Ghibli-style film grain |
Colorization
| Model | Description |
|---|---|
ddcolor-tiny |
DDColor colorization (lightweight) |
ddcolor-large |
DDColor colorization (high quality) |
deoldify / deoldify_fp16 |
DeOldify colorization (fp32 / fp16) |
deoldify_fixed / deoldify_fp16_fixed |
DeOldify with fixes (fp32 / fp16) |
Segmentation & Background Removal
| Model | Description |
|---|---|
RMBG-1.4 |
Background removal |
BiRefNet-lite-fp16 |
Bilateral reference segmentation (fp16) |
mediapipe-selfie-segmenter |
Person segmentation |
mediapipe-multiclass-segmenter |
Multi-class segmentation |
Classification
| Model | Description |
|---|---|
anime_real_cls-mobilenetv3 |
Anime vs. real photo classifier |
nima-mobilenet-quality |
Image quality assessment (NIMA) |
Usage
All models are in ONNX format and can be loaded with any ONNX-compatible runtime:
import onnxruntime as ort
session = ort.InferenceSession("realesrgan-general-plus.onnx")
result = session.run(None, {"input": input_tensor})
License
This repository contains models from multiple open-source projects, each with its own license. See LICENSE for details.
Model info
onnx
license:other
region:us
↓ 0
♥ 0
Created: 2026-03-09
Updated: 2026-03-13
View on Hugging FaceFiles (73)
.gitattributes
1x-aniscale2-refiner.onnx
ONNX
1x-artclarity.onnx
ONNX
1x-ghibli-grain.onnx
ONNX
1x-hurrdeblur-superultracompact.onnx
ONNX
1xDeH264_realplksr.onnx
ONNX
1xDeJPG_realplksr_otf.onnx
ONNX
1xDeNoise_realplksr_otf.onnx
ONNX
4xNomosWebPhoto_atd.onnx
ONNX
BiRefNet-lite-fp16.onnx
ONNX
LICENSE
NAFNet-GoPro-width64.onnx
ONNX
NAFNet-REDS-width64.onnx
ONNX
NAFNet-SIDD-width64.onnx
ONNX
README.md
RMBG-1.4.onnx
ONNX
SCUNet-GAN.onnx
ONNX
SCUNet-PSNR.onnx
ONNX
SPAN-4x.onnx
ONNX
SwinIR-4x-GAN.onnx
ONNX
anime_real_cls-mobilenetv3.onnx
ONNX
ddcolor-large.onnx
ONNX
ddcolor-tiny.onnx
ONNX
deoldify.onnx
ONNX
deoldify_fixed.onnx
ONNX
deoldify_fp16.onnx
ONNX
deoldify_fp16_fixed.onnx
ONNX
dncnn-color-blind.onnx
ONNX
dncnn-color-blind.onnx.data
maxim-deblurring-realblur-j.onnx
ONNX
maxim-deblurring-realblur-r.onnx
ONNX
maxim-deblurring-reds.onnx
ONNX
maxim-deblurring.onnx
ONNX
maxim-dehazing-indoor.onnx
ONNX
maxim-dehazing-outdoor.onnx
ONNX
maxim-denoising.onnx
ONNX
maxim-deraining-raindrop.onnx
ONNX
maxim-deraining.onnx
ONNX
maxim-enhancement.onnx
ONNX
maxim-retouching.onnx
ONNX
mediapipe-multiclass-segmenter.onnx
ONNX
mediapipe-selfie-segmenter.onnx
ONNX
nima-mobilenet-quality.onnx
ONNX
realcugan-2x-conservative.onnx
ONNX
realcugan-2x-conservative.onnx.data
realcugan-2x-denoise1x.onnx
ONNX
realcugan-2x-denoise1x.onnx.data
realcugan-2x-denoise2x.onnx
ONNX
realcugan-2x-denoise2x.onnx.data
realcugan-2x-denoise3x.onnx
ONNX
realcugan-2x-denoise3x.onnx.data
realcugan-2x-no-denoise.onnx
ONNX
realcugan-2x-no-denoise.onnx.data
realcugan-3x-conservative.onnx
ONNX
realcugan-3x-conservative.onnx.data
realcugan-3x-denoise3x.onnx
ONNX
realcugan-3x-denoise3x.onnx.data
realcugan-4x-conservative.onnx
ONNX
realcugan-4x-conservative.onnx.data
realcugan-4x-denoise3x.onnx
ONNX
realcugan-4x-denoise3x.onnx.data
realcugan-4x-no-denoise.onnx
ONNX
realcugan-4x-no-denoise.onnx.data
realesrgan-anime-fast.onnx
ONNX
realesrgan-anime-fast.onnx.data
realesrgan-anime-plus.onnx
ONNX
realesrgan-anime-plus.onnx.data
realesrgan-general-fast.onnx
ONNX
realesrgan-general-fast.onnx.data
realesrgan-general-plus.onnx
ONNX
realesrgan-general-plus.onnx.data
wasm/ort-wasm-simd-threaded.asyncify.wasm
wasm/vips.wasm
Related models
More from hugglyberry
No other models by this author.
More models
No task type declared.