apolinário

Very cool @takuma104, thanks a lot! cc @patrickvonplaten, @patil-suraj, @williamberman on best practices and trade-off of impact/modifications. I think this technique is showing how adding extra conditions to diffusion models...

I agree with @ryan-caesar-ramos , I think those serve different purposes and both could be part of a toolbox on diffusers. I think we would love a community contributed PR...

With the release soon(tm) of p2p-video, this gets even more relevant imo: https://video-p2p.github.io

Yes that is correct!

@patrickvonplaten , I think in this issue https://github.com/huggingface/diffusers/issues/1633 I showcase the code snippet used by AUTO1111 for using Karras sigmas for all samplers

I don't think they necessarily work better. It just works differently and the community enjoys having the possibility of having this variations for artistic purposes when using tools that support...

This is cool! I think potential next steps for making use of this that could be worth exploring would be: - [ ] Expose the `load_models` function to the UI,...

As https://github.com/gradio-app/gradio/issues/5033 was closed in favour of this one, I'd like to suggest expanding this issue to *all* components with `choices` (not only dropdown) And also I'd suggest this to...

From a UI/UX perspective imo the use-case of "either upload or record" is quite common and as you mentioned building this either/or system via tabs is a bit complex to...

> you could have 2 events, and in one of them, a component is required, but in the other, the component is not required Great point @abidlabs, what if the...