Rhea represents a combination of Proteus and Iris. The model is intended to be more accurate in preserving fine details than Iris, while also handling text in a less destructive way.
There are a few key limitations for this alpha that testers should know about:
Rhea currently only runs at 4x scale. Previews/exports set to other output sizes will fail.
The current version of the model is not fully optimized and speeds of this alpha are not representative of speeds users can expect when Rhea is released.
We’re very excited to have testers working with Rhea. Thanks as always for your feedback and testing.
When I set the destination folder in the Preferences there is no path shown and also no visible change after selecting a path so that it is not clear if the choosen path is taken by the application or not.
Did some testing. In my case the result are worse than Iris MQ. Iris creates more detail. Rhea softens the image more. Hair, eye lashes, lips etc are more detailed with Iris
I just find it a shame that we can run this model simply in 4x upscale and not the others, a shame to have limited on the resolution. After that it’s my opinion, but seeing the result with this model, there is still a lot of work to do on it, because a lot of artifacts on the images that we see moving. It would be good not to modify the parameters of this model like proteus and iris, for this model it would be good to do like the old Artemis, without being able to modify the parameters.
