For some reason I get blurry output on this particular model, like it has a layer of light haze on top. I get the same thing with the AzovyaRPG model, but haven't had this problem with others.

Hello!

Version 3.0 was made possible thanks to amazing model makers such as

@Zovya @Faeia @Lykon

This mix would not have been possible without their hard work which I respect immensly and would like to credit.

It's great to be back!

I'm looking for a checkpoint model which can draw clothing well - such as Jacket, Dress, Down Jackets, etc. looks like this model is a good one which has huge potentials... So please keep going and I'm happy to provide feedback and support!

Can you please mention some of the merged models? It's just good form to credit those people too

Great update for this model !

Can you also add the 2gb fp16 for the new version 3.0 ?

If somebody gets this error:

RuntimeError: CUDA error: the launch timed out and was terminated

CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.

For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

Restart the computer, try again and it should work. It worked for me =D

reproducability: 0

troll: 6/10

Ability to provide loras to prove it's not stolen: 2/10

and a ton of over prompting from autoprompt.

Though picture does have a lot of something to it to reeely make it something um "unique"

is there a particular vae you would recommend with this?