Current image generation models may be doing too much by asking a single model to simultaneously handle all aspects of scene creation — from understanding prompts and determining subject count to composition, identity preservation, and rendering.

0:46presented more than 20 papers at this year's CVPR, the computer vision and pattern recognition conference. Here's Fati explaining why image generation still has plenty of hard problems to solve. Maybe we are also asking a single model to solve too many difficult problems at once. Think about what happens when you generate a scene with several people. Now the model has to understand the problem. that I'm asking to model and then decide how many people

1:14should appear uh determine where they should be placed like the composition of the scene reason about their interactions because if there's a person if there's another person most likely there there is some connection preserve the identity of the person we can give okay this is my daughter this is my son and I want them to be in the picture not like any random person and finally render everything together in all a

1:39single process this. So maybe this is too much. I'm Sam Sharington and this is the TwiML AI podcast. For over a decade, I've been exploring the ideas and innovation shaping the future of AI through conversations [music] like this one that help you understand what's real, what's next, and what matters. Let's jump in. Yeah, that's a big difference that I see between I think even this conversation and the conversation we had last year.