相关论文: Aligning Text-to-Image Models using Human Feedback

Learning from feedback has been shown to enhance the alignment between text prompts and images in text-to-image diffusion models. However, due to the lack of focus in feedback content, especially regarding the object type and quantity,…

Learning from human feedback has shown success in aligning large, pretrained models with human values. Prior works have mostly focused on learning from high-level labels, such as preferences between pairs of model outputs. On the other…

Human feedback plays a critical role in learning and refining reward models for text-to-image generation, but the optimal form the feedback should take for learning an accurate reward function has not been conclusively established. This…

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-purpose text-to-image human preference reward model -- to effectively…

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 descriptions. However, many generated images still suffer from issues such as…

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

Text-to-image models often struggle to generate images that precisely match textual prompts. Prior research has extensively studied the evaluation of image-text alignment in text-to-image generation. However, existing evaluations primarily…

We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students…

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. Instead of laborious human engineering, we propose prompt adaptation,…

Large text-to-video models hold immense potential for a wide range of downstream applications. However, they struggle to accurately depict dynamic object interactions, often resulting in unrealistic movements and frequent violations of…

Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…

Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization…

Recent progress in generative models, especially in text-guided diffusion models, has enabled the production of aesthetically-pleasing imagery resembling the works of professional human artists. However, one has to carefully compose the…

Pretrained language models often do not perform tasks in ways that are in line with our preferences, e.g., generating offensive text or factually incorrect summaries. Recent work approaches the above issue by learning from a simple form of…

Text-to-image generative models are a new and powerful way to generate visual artwork. However, the open-ended nature of text as interaction is double-edged; while users can input anything and have access to an infinite range of…

Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and…

Recently, diffusion-based deep generative models (e.g., Stable Diffusion) have shown impressive results in text-to-image synthesis. However, current text-to-image models often require multiple passes of prompt engineering by humans in order…

3D content creation from text prompts has shown remarkable success recently. However, current text-to-3D methods often generate 3D results that do not align well with human preferences. In this paper, we present a comprehensive framework,…

Fine-tuning text-to-image models with reward functions trained on human feedback data has proven effective for aligning model behavior with human intent. However, excessive optimization with such reward models, which serve as mere proxy…

Recent advances in text-to-video (T2V) generative models have shown impressive capabilities. However, these models are still inadequate in aligning synthesized videos with human preferences (e.g., accurately reflecting text descriptions),…