This was sooo difficult to make it not mix tongue and teeth. How does it work on your images?

With some text guidance it can do the correct number of fingers. this was a 60x90px image upscaled by 4x

I plan to get another deep learning server to continue my research for better upscaling models

visualizing where my model adds and removes color to an image during training

as training goes on, the learned residual maps get more detailed

Since the test runs provide very good results, I will start training a 10GB model starting next week on my new rtx5090. I will probably take weeks to months until it is ready

Both images are from small test models after 60k iterations. One is my old model. The other is my new model. both models are similar in size. both are trained using esrgan.

still training...

first 21k steps (700k patches seen)

as training goes on, here are evaluation samples taken after around 500k, 700k, and 1M patches seen

sample image generated after 1.9M patches seen. i think the hands look better compared to what the diffuser generates, mostly because the number of fingers is correct

I offer a generous daily free quota. As of now, a single ip can get up to 2 minutes compute time on rtx5090 for free daily. It is important to protect the site from users cheating around this limit. Any ip cheating will be banned. False Positives are < 0.1%. No more exceptions!

if you are banned and it is truly an accident, get a new ip and wait 24 hours before you submit a new request. Do not send a pic to your friend and have him upscale it for you. This is considered cheating on the daily free quota

Now I'm sidetracked again. Guess what I'm cooking up here...

youtu.be/81Aeg-Q6sbI

pypi project for upscaling api pypi.org/project/image-…

image-upscaling.net/pages/best-ima…