Filtered to diffusion models · clear filter
This paper introduces a new framework for building strong image generators that can produce highly photorealistic images while accurately following editing instructions. Practitioners might care about the potential applications of this framework in fields like computer vision, graphics, and art.
This paper introduces a new method for reinforcement learning with diffusion models, called DiffusionART, which combines the benefits of forward-process and reverse-process methods to improve efficiency and stability. Practitioners might care about this method because it can train diffusion models more effectively and efficiently than existing methods.
This paper improves the performance of representation autoencoders (RAEs) by training a decoder to work with different layers of a pre-trained visual encoder, rather than relying on a fixed layer fusion. A practitioner might care about this because it allows for more flexible and robust image generation.
This paper proposes a new method to process images only when necessary in diffusion vision-language models, reducing unnecessary computations and maintaining high accuracy. Practitioners caring about efficient model performance might be interested in this approach.