Key-Locked Rank One Editing for Text-to-Image Personalization · HackerPapers discussions

Key-Locked Rank One Editing for Text-to-Image Personalization — mentioned by Terretta

Sun, 06 Aug 2023 14:05:13 GMT

From the white paper on Arxiv: “This allows runtime-efficient balancing of visual-fidelity and textual-alignment with a single 100KB trained model, which is five orders of magnitude smaller than the current state of the art.” https://arxiv.org/abs/2305.01644 It's one of those sentences that if you know what it means, you know what it means. That said, the title needs the word "personalization" inserted before the word model, e.g.: Nvidia intros 100kb text-to-image personalization model called Perfusion

Paper and discussion history. A mention is not an endorsement.

Key-Locked Rank One Editing for Text-to-Image Personalization — mentioned by Jackson__

Wed, 02 Aug 2023 20:26:58 GMT

I can't figure out if the author is clickbaiting, or honestly does not know that you still need the base diffusion model to use this? >Nvidia's new Perfusion image generator Calls it an image generator, when it isn't. >In the rapidly evolving landscape of AI art creation tools, Nvidia researchers have introduced an innovative new text-to-image personalization method called Perfusion. A spark of understanding, that it is in fact not an image model on its own. >But it’s not a million-dollar super heavyweight model like its competitors. And immediately fails to comprehend what "personalization…

Paper and discussion history. A mention is not an endorsement.

Key-Locked Rank One Editing for Text-to-Image Personalization — mentioned by peter_d_sherman

Tue, 01 Aug 2023 23:42:59 GMT

Related: Paper: "Key-Locked Rank One Editing for Text-to-Image Personalization": https://arxiv.org/pdf/2305.01644.pdf

Paper and discussion history. A mention is not an endorsement.