Hugging Face's logo

baker76
/
upscale-models

Image-to-Image
ONNX
super-resolution
upscaling
image-upscaling
Model card Files
xet
 Community
benbaker76 commited on
Commit
a2fe039
·
verified ·
1 Parent(s): 5e6510f

Add MewZoom_V1_UNet_x4_int8 (8-bit weights)

Browse files
Files changed (2) hide show
  1. MewZoom_V1_UNet_x4_int8.onnx +3 -0
  2. README.md +28 -26
MewZoom_V1_UNet_x4_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c9d5d1eb8d5295ce2cace2054f1ece2c0d8d149f1c36b500af34806a67655c2
3
+ size 129866207
README.md CHANGED
@@ -19,37 +19,39 @@ Each model is the original author's weights converted to ONNX by upscale's
19
  `python/export_onnx.py`: opset and input/output naming are the same across all of them, and
20
  height and width are dynamic so an image can be run whole or in tiles. Most come in two
21
  precisions, `<name>.onnx` (float32 weights) and `<name>_fp16.onnx` (float16 weights, float32
22
- input and output), which give the same picture to within one 8-bit level.
 
 
23
 
24
  **Nothing here was trained by this organization.** Every file is a conversion, and each
25
  remains under the license its author released the original weights under - follow the source
26
  link for the terms, which for some models restrict commercial use.
27
 
28
- | Model | Scale | fp32 | fp16 | Architecture | Original weights |
29
- | --- | --- | --- | --- | --- | --- |
30
- | `APISR_GRL_x4` | x4 | 27.1 MB | 17.5 MB | GRL | [HikariDawn/APISR](https://huggingface.co/HikariDawn/APISR) |
31
- | `APISR_RRDB_x2` | x2 | 18.7 MB | 9.8 MB | RRDBNet-6B | [HikariDawn/APISR](https://huggingface.co/HikariDawn/APISR) |
32
- | `AnimeSharpV2_ESRGAN_Soft_x2` | x2 | 70.0 MB | 36.6 MB | ESRGAN | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
33
- | `AnimeSharpV2_MoSR_Sharp_x2` | x2 | 18.0 MB | 9.4 MB | MoSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
34
- | `AnimeSharpV2_MoSR_Soft_x2` | x2 | 18.0 MB | 9.4 MB | MoSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
35
- | `AnimeSharpV2_RPLKSR_Sharp_x2` | x2 | 30.8 MB | 16.1 MB | RealPLKSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
36
- | `AnimeSharpV2_RPLKSR_Soft_x2` | x2 | 30.8 MB | 16.1 MB | RealPLKSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
37
- | `AnimeSharpV3_x2` | x2 | 70.0 MB | 36.6 MB | ESRGAN | [Kim2091/AnimeSharpV3](https://huggingface.co/Kim2091/AnimeSharpV3) |
38
- | `BSRGAN_x2` | x2 | 69.7 MB | 36.4 MB | RRDBNet | [kadirnar/BSRGANx2](https://huggingface.co/kadirnar/BSRGANx2) |
39
- | `MewZoom_V1_UNet_x4` | x4 | 517.2 MB | 258.9 MB | MewZoom U-Net | [andrewdalpino/MewZoom-V1-4X-Unet](https://huggingface.co/andrewdalpino/MewZoom-V1-4X-Unet) |
40
- | `RealESRGAN_anime_x4` | x4 | 18.7 MB | 9.8 MB | RRDBNet-6B | [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) |
41
- | `RealESRGAN_x2` | x2 | 70.0 MB | 36.6 MB | RRDBNet | [ai-forever/Real-ESRGAN](https://huggingface.co/ai-forever/Real-ESRGAN) |
42
- | `RealESRGAN_x4` | x4 | 69.9 MB | 36.5 MB | RRDBNet | [ai-forever/Real-ESRGAN](https://huggingface.co/ai-forever/Real-ESRGAN) |
43
- | `RealESRGAN_x4plus` | x4 | 69.9 MB | 36.5 MB | RRDBNet | [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) |
44
- | `RealESRGAN_x8` | x8 | 70.0 MB | 36.6 MB | RRDBNet | [ai-forever/Real-ESRGAN](https://huggingface.co/ai-forever/Real-ESRGAN) |
45
- | `RealESR_General_x4` | x4 | 5.0 MB | 2.5 MB | SRVGGNetCompact | [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) |
46
- | `RealWebPhoto_RGT_x4` | x4 | 92.3 MB | - | RGT | [Phips/4xRealWebPhoto_RGT](https://huggingface.co/Phips/4xRealWebPhoto_RGT) |
47
- | `Swin2SR_Classical_x2` | x2 | 72.4 MB | 40.0 MB | Swin2SR | [mv-lab/swin2sr](https://github.com/mv-lab/swin2sr) |
48
- | `Swin2SR_Classical_x4` | x4 | 73.0 MB | 40.3 MB | Swin2SR | [mv-lab/swin2sr](https://github.com/mv-lab/swin2sr) |
49
- | `Swin2SR_RealWorld_x4` | x4 | 72.3 MB | 39.9 MB | Swin2SR | [mv-lab/swin2sr](https://github.com/mv-lab/swin2sr) |
50
- | `SwinIR_BSRGAN_x4` | x4 | 55.2 MB | - | SwinIR-M | [mikestealth/SwinIR](https://huggingface.co/mikestealth/SwinIR) |
51
- | `UltraMix_Smooth_x4` | x4 | 69.9 MB | 36.5 MB | ESRGAN | [Kim2091/UltraSharp](https://huggingface.co/Kim2091/UltraSharp) |
52
- | `UltraSharp_x4` | x4 | 69.9 MB | 36.5 MB | ESRGAN | [Kim2091/UltraSharp](https://huggingface.co/Kim2091/UltraSharp) |
53
 
54
  ## Using a file directly
55
 
 
19
  `python/export_onnx.py`: opset and input/output naming are the same across all of them, and
20
  height and width are dynamic so an image can be run whole or in tiles. Most come in two
21
  precisions, `<name>.onnx` (float32 weights) and `<name>_fp16.onnx` (float16 weights, float32
22
+ input and output), which give the same picture to within one 8-bit level. A few also come as
23
+ `<name>_int8.onnx`: 8-bit weights, turned back to float32 as the network runs, a quarter of the
24
+ size and within two levels of float32.
25
 
26
  **Nothing here was trained by this organization.** Every file is a conversion, and each
27
  remains under the license its author released the original weights under - follow the source
28
  link for the terms, which for some models restrict commercial use.
29
 
30
+ | Model | Scale | fp32 | fp16 | int8 | Architecture | Original weights |
31
+ | --- | --- | --- | --- | --- | --- | --- |
32
+ | `APISR_GRL_x4` | x4 | 27.1 MB | 17.5 MB | - | GRL | [HikariDawn/APISR](https://huggingface.co/HikariDawn/APISR) |
33
+ | `APISR_RRDB_x2` | x2 | 18.7 MB | 9.8 MB | - | RRDBNet-6B | [HikariDawn/APISR](https://huggingface.co/HikariDawn/APISR) |
34
+ | `AnimeSharpV2_ESRGAN_Soft_x2` | x2 | 70.0 MB | 36.6 MB | - | ESRGAN | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
35
+ | `AnimeSharpV2_MoSR_Sharp_x2` | x2 | 18.0 MB | 9.4 MB | - | MoSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
36
+ | `AnimeSharpV2_MoSR_Soft_x2` | x2 | 18.0 MB | 9.4 MB | - | MoSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
37
+ | `AnimeSharpV2_RPLKSR_Sharp_x2` | x2 | 30.8 MB | 16.1 MB | - | RealPLKSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
38
+ | `AnimeSharpV2_RPLKSR_Soft_x2` | x2 | 30.8 MB | 16.1 MB | - | RealPLKSR | [Kim2091/AnimeSharpV2](https://huggingface.co/Kim2091/AnimeSharpV2) |
39
+ | `AnimeSharpV3_x2` | x2 | 70.0 MB | 36.6 MB | - | ESRGAN | [Kim2091/AnimeSharpV3](https://huggingface.co/Kim2091/AnimeSharpV3) |
40
+ | `BSRGAN_x2` | x2 | 69.7 MB | 36.4 MB | - | RRDBNet | [kadirnar/BSRGANx2](https://huggingface.co/kadirnar/BSRGANx2) |
41
+ | `MewZoom_V1_UNet_x4` | x4 | 517.2 MB | 258.9 MB | 129.9 MB | MewZoom U-Net | [andrewdalpino/MewZoom-V1-4X-Unet](https://huggingface.co/andrewdalpino/MewZoom-V1-4X-Unet) |
42
+ | `RealESRGAN_anime_x4` | x4 | 18.7 MB | 9.8 MB | - | RRDBNet-6B | [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) |
43
+ | `RealESRGAN_x2` | x2 | 70.0 MB | 36.6 MB | - | RRDBNet | [ai-forever/Real-ESRGAN](https://huggingface.co/ai-forever/Real-ESRGAN) |
44
+ | `RealESRGAN_x4` | x4 | 69.9 MB | 36.5 MB | - | RRDBNet | [ai-forever/Real-ESRGAN](https://huggingface.co/ai-forever/Real-ESRGAN) |
45
+ | `RealESRGAN_x4plus` | x4 | 69.9 MB | 36.5 MB | - | RRDBNet | [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) |
46
+ | `RealESRGAN_x8` | x8 | 70.0 MB | 36.6 MB | - | RRDBNet | [ai-forever/Real-ESRGAN](https://huggingface.co/ai-forever/Real-ESRGAN) |
47
+ | `RealESR_General_x4` | x4 | 5.0 MB | 2.5 MB | - | SRVGGNetCompact | [xinntao/Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) |
48
+ | `RealWebPhoto_RGT_x4` | x4 | 92.3 MB | - | - | RGT | [Phips/4xRealWebPhoto_RGT](https://huggingface.co/Phips/4xRealWebPhoto_RGT) |
49
+ | `Swin2SR_Classical_x2` | x2 | 72.4 MB | 40.0 MB | - | Swin2SR | [mv-lab/swin2sr](https://github.com/mv-lab/swin2sr) |
50
+ | `Swin2SR_Classical_x4` | x4 | 73.0 MB | 40.3 MB | - | Swin2SR | [mv-lab/swin2sr](https://github.com/mv-lab/swin2sr) |
51
+ | `Swin2SR_RealWorld_x4` | x4 | 72.3 MB | 39.9 MB | - | Swin2SR | [mv-lab/swin2sr](https://github.com/mv-lab/swin2sr) |
52
+ | `SwinIR_BSRGAN_x4` | x4 | 55.2 MB | - | - | SwinIR-M | [mikestealth/SwinIR](https://huggingface.co/mikestealth/SwinIR) |
53
+ | `UltraMix_Smooth_x4` | x4 | 69.9 MB | 36.5 MB | - | ESRGAN | [Kim2091/UltraSharp](https://huggingface.co/Kim2091/UltraSharp) |
54
+ | `UltraSharp_x4` | x4 | 69.9 MB | 36.5 MB | - | ESRGAN | [Kim2091/UltraSharp](https://huggingface.co/Kim2091/UltraSharp) |
55
 
56
  ## Using a file directly
57