ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
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 encode human preferences. Its training is based on our systematic annotation pipeline including rating and ranking, which collects 137k expert comparisons to date. In human evaluation, ImageReward outperforms existing scoring models and metrics, making it a promising automatic metric for evaluating text-to-image synthesis. On top of it, we propose Reward Feedback Learning (ReFL), a direct tuning algorithm to optimize diffusion models against a scorer. Both automatic and human evaluation support ReFL's advantages over compared methods. All code and datasets are provided at \url{https://github.com/THUDM/ImageReward}.
Code (3)
Tasks
Image GenerationPreference MappingText to Image GenerationText-to-Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Test-Time Reasoning Through Visual Human Preferences with VLMs and Soft Rewards
Can Visual Language Models (VLMs) effectively capture human visual preferences? This work addresses this question by training VLMs to think about preferences at test time, employing reinforcement learning methods inspire…
World KnowledgeListener-Rewarded Thinking in VLMs for Image Preferences
Training robust and generalizable reward models for human visual preferences is essential for aligning text-to-image and text-to-video generative models with human intent. However, current reward models often fail to gen…
MemorizationReinforcement Learning (RL)Aligning Diffusion Models by Optimizing Human Utility
We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility. Since this objective applies to each generation…
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
The default paradigm of post-training text-to-image generators includes post-hoc selection of generated images, and subsequent training with one reward model to align the generator to the reward, typically user preferenc…
Evaluating Text-to-Image Synthesis with a Conditional Fréchet Distance
Evaluating text-to-image synthesis is challenging due to misalignment between established metrics and human preferences. We propose cFreD, a metric based on the notion of Conditional Fr\'echet Distance that explicitly ac…
BenchmarkingImage Generation