Bosco Yung

Hi, thanks for your interest in the library! Do you mean allowing the user to specify the *frame range* of the given video to be predicted on?

The idea sounds good and I shall consider including this feature. Nonetheless, please understand that I could not give any timetable for now. :)

Just a pure guess: In a text-to-image model like Stable Diffusion, the noisy latent image is de-noised while conditioned on text embeddings. So what Midjourney did here could be using...

Hello! Thank you very much for your interest in the library and the suggestion! Currently we have no plans to manage an official Docker image. However, it is indeed a...

Hello! I didn't realise that this thread is already more than one year old... Not sure if this is still relevant, but in case you are interested, please install the...