Adding Conditional Control to Text-to-Image Diffusion Models · HackerPapers discussions

Adding Conditional Control to Text-to-Image Diffusion Models — mentioned by mdp2021

Wed, 01 Mar 2023 08:14:43 GMT

So, technically, and beyond that, theoretically, and even anatomically. In the brain, visual processing, left hemisphere was found to contain details; a right hemisphere to contain structural relations. So a whole is composed of elements and relative positions. In Convolutional Neural Networks, "near, direct" layers contain analytic detail and "far, abstract" layers contain synthetic shapes. So, implementation-wise, you can take e.g. descriptions as abstracts and a "pre-acquired" memory of details as «graphic». Edit: About the "combination", well that the whole purpose of this new technology…

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

Adding Conditional Control to Text-to-Image Diffusion Models — mentioned by zsikelianos

Tue, 28 Feb 2023 23:41:11 GMT

Hey, Scribble Diffusion author here. Thanks for your kind words and feedback. I love seeing all these links to your scribbles. I'm an engineer at Replicate, which is a place to run ML models in the cloud. [0] We built Scribble Diffusion as an open-source app [1] to demonstrate how to use Replicate. This is all built on ControlNet [2], a brilliant technique by Lvmin Zhang and Maneesh Agrawala [3] for conditioning diffusion models on additional sources, in this case human scribbles. It also allows for controlling Stable Diffusion using other inputs like pose estimation, edge detection, and…

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