Downloads · 30 days
0
2xHFA2kAVCCompact
Phips/2xHFA2kAVCCompact
2xHFA2kAVCCompact is a image-to-image model from Phips. Use it when you need one image transformed into another. The card lists the license as cc-by-4.0.
Access
Public
Updated Oct 8, 2024
Repo size
1.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.2 MB · 100%
At a glance
- Task
- Image-to-Image
- License
- cc-by-4.0
- Access
- Public
- Created
- Oct 7, 2024
- Updated
- Oct 8, 2024
- SHA
- 8ba07f8c
Model card
From the Hugging Face model README
2xHFA2kAVCCompact
Name: 2xHFA2kAVCCompact
Author: Philip Hofmann
Release Date: 18.06.2023
License: CC BY 4.0
Network: SRVGGNet
Scale: 2
Purpose: Fast 2x anime upscaling model that handles AVC (h264) degradation
Iterations: 111,000
batch_size: 4
HR_size: 256
Dataset: HFA2k_h264
Number of train images: 2568
OTF Training: No
Pretrained_Model_G: None
Description: 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 the HFA2k dataset with Kim's dataset destroyer.
- Task
- Image-to-Image
- License
- cc-by-4.0
- Created
- Oct 7, 2024
- Updated
- Oct 8, 2024