Basu Jindal

> Hello, great job! Can you please tell me how to add a ready-made mask for the image? Hi, I will add this feature for the gradio interface in a...

Thank you for the suggestion, will add these factors in the GUI too, and hopefully push the changes today. Cheers!

Hi, I looked into it but changing these values would require a change in some of the config file values too. I am unsure about the exact values to change...

> Using `python optimizedSD\optimized_txt2img.py --from-file optimizedSD/prompts.txt --H 512 --W 512 --n_iter 1 --n_samples 5 --ddim_steps 50 --precision full` I would expect there to be an output folder named after every...

Hi, I cannot reproduce this issue, does img2img_gradio.py work fine for you?

Hi, the image dimension (--H, --W) should be a multiple of 64, else it gives this error.

> img2img has an initial spike in GPU VRAM: > >  > > Can this step be done on CPU? Does this graph represent the entire image generation process...

I am sorry if it is a wrong question, but don't we need padding token to train model with bs > 1, or are they concatenating sentences together, separated by...

It is not advisable to discuss "leaked weights" in this repository. Anyways they will be releasing the official weights today.

> Is there a way to change the GPU it uses? I have two cards, a 1080 TI on slot 0 and a 1660 TI on slot 1, but then...