Simo Ryu

Sure thing. right now Im not so familiar with Gradio, but Ill look forward to add these in A1111 extension

For anyone elses information, there is canonical request on a1111's repo as well. https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/4406 , which is very constructive and relevant.

Can you show us more of the code configuration or error messages? Did you set `.env` file with HF token?

I think so. You can take tiny timesteps to make this exactly same formulation as diffusion models, so DDIM inversion would still work here. if it is really consistent, it...

@zhihongp that's a good point. I'm not sure about why CT is not as good empirically, but "theoretically", it should have no difference (as two loss term has $o(t)$ that...

Empirically, similar phenomena happens *all the time in deep learning*, where... * Self-supervision with data A and using that pretrained model to model A (https://arxiv.org/abs/2209.14389) * Overparameterization and compression is...

This is known issue since LoRA format is different. We will work on this in the future. Thanks!

I assume this can be fixed with pre-processing? Python packages mentioned here https://stackoverflow.com/questions/54395735/how-to-work-with-heic-image-file-types-in-python can be used?

Checked all the stuff you mentioned. train_text_encoder must be on in current implementation, but I'm going to update it in the future. #5