Dookie
Dookie
Temporary fix works for me. Any ideas if voice cloning (--speaker_wav /path/to/sample.wav) also works via tts-server? If yes and we can successfully use this parameter in the GET-request, where should...
This would explain why my final trained model always gives me the exact same images as the original stable diffusion v2.1 768px model. Since my RTX 4080 is limited to...
Nice, thank you @pcuenca
I think I have a similar or related issue. I created an image with diffusers and auto1111 with the same parameters, but got different images, with diffusers being worse quality...
@patrickvonplaten Good finding. This indeed solved my issue. And I don't have washed out colors btw. Thank you so much! Before:  After code correction:  Still slightly different than...
Interestingly today it's using libbitsandbytes_cudaall.dll. Don't really know what changed... How can I influence what version is used? I think I re-ran accelerate config for the venv. I guess this...
I figured out what was going on. Since bitsandbytes unfortunately does not support windows officially, a dreambooth extension (https://github.com/d8ahazard/sd_dreambooth_extension/tree/main/bitsandbytes_windows) I installed earlier in the same conda venv made this work...
I've run this command: ``` SET MODEL_NAME="stabilityai/stable-diffusion-2-1" SET INSTANCE_DIR="some/path/to/training_pics" SET CLASS_DIR="some/path/to/class_pics" SET OUTPUT_DIR="some/path/to/output_directory" accelerate launch examples\dreambooth\train_dreambooth.py ^ --pretrained_model_name_or_path=%MODEL_NAME% ^ --revision="fp16" ^ --instance_data_dir=%INSTANCE_DIR% ^ --class_data_dir=%CLASS_DIR% ^ --output_dir=%OUTPUT_DIR% ^ --with_prior_preservation --prior_loss_weight=1.0 ^...
I also have the problem after I read generation parameters from an image, I can't switch models anymore. After hitting generate the same model used to generate the image is...
I just found out that you prevent the bug and enable model switching again, if you check the following option in settings->user interface: `When reading generation parameters from text into...