CVAug 13, 2024
Imagen 3
Imagen-Team-Google, Jason Baldridge, Jakob Bauer, Mukul Bhutani, Nicole Brichtova, Andrew Bunner, Lluis Castrejon, Kelvin Chan, Yichang Chen, Sander Dieleman, Yuqing Du, Zach Eaton-Rosen
arXiv:2408.07009v329 citationsh-index: 3
Originality Synthesis-oriented
AI Analysis
This work addresses image generation for AI applications, but appears incremental as it builds on existing latent diffusion models.
The paper tackles the problem of generating high-quality images from text prompts using Imagen 3, a latent diffusion model, and reports that it is preferred over other state-of-the-art models in evaluations.
We introduce Imagen 3, a latent diffusion model that generates high quality images from text prompts. We describe our quality and responsibility evaluations. Imagen 3 is preferred over other state-of-the-art (SOTA) models at the time of evaluation. In addition, we discuss issues around safety and representation, as well as methods we used to minimize the potential harm of our models.