Just learned that you can generate image using text to image using base model then send it to img2img and use refiner model with around 0.33 to 0.25 strength.

So from what I understand, all you need is the base for A1111. If you’re using comfyUI, might want to download the refiner too.

What are you using? With A1111 I had the same problem, had to add in the - - no-half-vae in the batch file for the command line

Have you tried homebrew on LG TVs? https://youtu.be/3pLEwQuidII

They also mentioned that they are waiting to confirm if the lora models trained on 0.9 are working with 1.0. In my opinion, anything that was trained on 0.9 should not be holding up a major release.

Here is decent tutorial: https://www.youtube.com/watch?v=KTPLOqAMR0s&ab_channel=SebastianKamph

This is bull in my opinion, 0.9 was supposed to be a leak, why the hell are they delaying the release for a bootleg (for all intends and purposes)!

https://www.instagram.com/shannonmcmu