311_code

> > I forgot to mention for this upcoming workflow I made for SVD, I also do batch whole_image input of 48-96 random generated images, or you can use real...

How the heck does live preview still not work on newest version of defoum and automatic? That's half of the fun of using the deforum extension, seeing the preview generate...

I take it back I checked and it runs at about 4 fps on my 4090 in depthviewer with depth-anythibg large model. If I try your idea with the xformers...

So i spent about 4 hours trying to modify the "record from microphone" button toggle behavior on the whisper-stt extension. Which apparantly has limitations though because of how gradio works....

The fix above me by Johnnystreet worked for me, I had mutiple modeling_phi.py files, and used the one under` C:\Users\NewPC\.cache\huggingface\modules\transformers_modules\vikhyatk\moondream1\f6ebunchofcharacters` I was trying to use this workflow https://comfyworkflows.com/workflows/b703fa8b-5fe0-4678-8692-021766a891c4 and followed...

I just updated my comment, it works after I tried his code out.

> Any chance of adding a feature where you can take an SBS stereo image, one that contains a different angle for each side, e.g. left side is a photo...

I would also like to know if I could train on existing videos of myself. This could be very useful for a LLM chat I'm working on trained on company...

Crickets for some reason, I'd like to know also.

The dev said it's only for comic generation for now. There is no code related to the video generation that I see either, all looks pretty comic to me.