Alejandro Gil
Alejandro Gil
This PR adds a small but kind of important QOL change that I made, it will add an option to customize the `Cutn` value from the web interface.  By...
It seems that when using the value `-1` on the Num steps on the app it will not save anything once you hit the stop button, according to the tooltip...
Hi there, I created recently a PR (#20) with some small QOL improvements and after that I decided to continue improving the code a bit so it was easier to...
This changes in the `taming/data/custom.py` file allow the use of folders for the training and validation paths while been compatible with how it was used before. This should make it...
As of now it seems like you need to use a list of prompts and seeds in order to be able to run stable diffusion videos, it would be nice...
Just like the upsample option but for face restoration using something like GFPGAN, RestoreFormer or similar models, this would allow us to just pass an argument to the walk function...
As the title says it would be nice to have an option to be able to specify the output video path as well as its filename independently of the output_dir...
With the current implementation the `name` argument is replaced with a timestamp/date when you set it to None or leave it empty, this makes the directory have a different name...
Maybe I didn't see it and it is already implemented but it would be nice to have a callback option which is executed every X number of steps, it would...
Hi there, it seems like the `run_lm_finetuning.py` script from GPT2-HarryPotter-Training can't be resumed once its stopped, when trying to resume from a checkpoint using the path to the checkpoint on...