sd-scripts
sd-scripts copied to clipboard
kohya-ss
Hi thanks so much for your work with the LoRA training, its been a blast I was thinking it would be a good help if the training parameters used for...
References https://github.com/huggingface/diffusers/blob/main/examples/community/README.md#stable-diffusion-with-k-diffusion https://github.com/crowsonkb/k-diffusion
It would be great to make caching the image latents optional. It takes 12 hours to convert 100k images with left/right flip enabled on a 3090 :/ (2.6 it/s). If...
Much like the stable diffusion A1111 repo and the other dreambooth scripts out there, I would like to recommend adding the Interrupt function and support for image generation at each...
I see that the arg `--v2` is optional, but it does not get used at all in "prepare bucket latents.py". Might want to remove it if its not going to...
Each concept can have a different repeat in DreamBooth method. But metadata .json (fine tuning method) does not have the feature. One idea is that the folder name for fine...
Currently the epoch starts from 1 when resuming. It is better to be able to set arbitrary number by argument. (Or automatically taken from the file name.)
The implementation of Textual Inversion in Diffusers is different from CompVis. So, it might be required to implement that from scratch. - https://github.com/rinongal/textual_inversion - https://github.com/huggingface/diffusers/tree/main/examples/textual_inversion
Recently the model gets overtrained much quicker than before with same hyper parameters What could be the change? Can it be these new settings set like this default?  Here...
