multimodalart's picture
Squashing commit
4450790 verified
|
raw
history blame
4.06 kB

Comparisons

Comparisons among different model versions

Note that V1.3 is not always better than V1.2. You may need to try different models based on your purpose and inputs.

Version Strengths Weaknesses
V1.3 โœ“ natural outputs
โœ“better results on very low-quality inputs
โœ“ work on relatively high-quality inputs
โœ“ can have repeated (twice) restorations
โœ— not very sharp
โœ— have a slight change on identity
V1.2 โœ“ sharper output
โœ“ with beauty makeup
โœ— some outputs are unnatural

For the following images, you may need to zoom in for comparing details, or click the image to see in the full size.

Input V1 V1.2 V1.3
019_Anne_Hathaway_01_00
106_Harry_Styles_00_00
076_Paris_Hilton_00_00
008_George_Clooney_00_00
057_Madonna_01_00
044_Amy_Schumer_01_00
012_Jackie_Chan_01_00