AbstractEyes
AbstractEyes
I might get this implemented on my branch before the end of the weekend. If that's the case I'll make a PR. I've devised a method to train MIN_SNR in...
I'm getting this without the prompt being modified. The thing reloads each time as of the current build using Flux. Loads, spins up, finishes, unloads everything. Has to reload slowly...
> > I'm getting this without the prompt being modified. The thing reloads each time as of the current build using Flux. Loads, spins up, finishes, unloads everything. Has to...
> Collaborator No. Happens even when I leave the seed the same and have unfinished generations. The vram visually drops to nearly nothing and then loads about half instantly so...
So I noticed it wasn't happening with ALL other models. Primarily this one. When I load fp8 unet with the fp16 xxl as standalone it doesn't need to reload every...
> > So I noticed it wasn't happening with ALL other models. Primarily this one. When I load fp8 unet with the fp16 xxl as standalone it doesn't need to...
Same problem, also using the 4090. Seems like the thing won't even let me train a Lora either, it's just disabled by default. I was trying to use dreambooth training...
Seems like the scripts still do not support the refiner.
Please provide more details and an error log.
Is it ready yet?