Hope topaz add "LDSR stable diffusion img2img upscale" model concept look alike

Video AI Ideas
, ,
5

I agree with you.
But from the images posted by OP. It didn’t generate anything new in the image.
It seem that he only use the upscale features come with Stable Diffusion.
The backgroud is upscaled by “Latent Diffusion Super Resolution (LDSR) upscaler” and the human face is upscaled by “GPFGAN”.

I can do similar upscaling using CodeFormer. (Not as detail as LDSR but faster)

000000_CodeFormer-Video_15fps
000000_CodeFormer-Video_15fps1366×1024 106 KB

Compare:
Left: Origin Middle:CodeFormer Right:Prob-3 Auto

compare
compare1920×1038 83.9 KB

Source Video:
https://youtu.be/jNQXAC9IVRw