We present a comprehensive solution to learn and improve text-to-image models from
human preference feedback. To begin with, we build ImageReward---the first general …

Recent text-to-image generative models can generate high-fidelity images from text inputs,
but the quality of these generated images cannot be accurately evaluated by existing …

Deep generative models have shown impressive results in text-to-image synthesis.
However, current text-to-image models often generate images that are inadequately aligned …

Human evaluation is critical for validating the performance of text-to-image generative
models, as this highly cognitive process requires deep comprehension of text and images …

The ability to collect a large dataset of human preferences from text-to-image users is
usually limited to companies, making such datasets inaccessible to the public. To address …

Abstract Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen
have made significant progress in generating high-resolution images based on text …

Well-designed prompts can guide text-to-image models to generate amazing images.
However, the performant prompts are often model-specific and misaligned with user input …

Text-to-image generative models often reflect the biases of the training data, leading to
unequal representations of underrepresented groups. This study investigates inclusive text …

Driven by the scalable diffusion models trained on large-scale datasets text-to-image
synthesis methods have shown compelling results. However these models still fail to …

Recent text-to-image (T2I) diffusion models show outstanding performance in generating
high-quality images conditioned on textual prompts. However, they fail to semantically align …