Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization

• URL: http://arxiv.org/abs/2406.06382v1
• Date: Mon, 10 Jun 2024 15:42:03 GMT
• Title: Diffusion-RPO: Aligning Diffusion Models through Relative Preference Optimization
• Authors: Yi Gu, Zhendong Wang, Yueqin Yin, Yujia Xie, Mingyuan Zhou,
• Abstract summary: We introduce Diffusion-RPO, a new method designed to align diffusion-based T2I models with human preferences more effectively. We have developed a new evaluation metric, style alignment, aimed at overcoming the challenges of high costs, low interpretability. Our findings demonstrate that Diffusion-RPO outperforms established methods such as Supervised Fine-Tuning and Diffusion-DPO in tuning Stable Diffusion versions 1.5 and XL-1.0.
• Score: 68.69203905664524
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory. The Diffusion-DPO technique made initial strides by employing pairwise preference learning in diffusion models tailored for specific text prompts. We introduce Diffusion-RPO, a new method designed to align diffusion-based T2I models with human preferences more effectively. This approach leverages both prompt-image pairs with identical prompts and those with semantically related content across various modalities. Furthermore, we have developed a new evaluation metric, style alignment, aimed at overcoming the challenges of high costs, low reproducibility, and limited interpretability prevalent in current evaluations of human preference alignment. Our findings demonstrate that Diffusion-RPO outperforms established methods such as Supervised Fine-Tuning and Diffusion-DPO in tuning Stable Diffusion versions 1.5 and XL-1.0, achieving superior results in both automated evaluations of human preferences and style alignment. Our code is available at https://github.com/yigu1008/Diffusion-RPO

Related papers

• Aligning Diffusion Models with Noise-Conditioned Perception [42.042822966928576]
  Diffusion Models typically optimize in pixel or VAE space, which does not align well with human perception. We propose using a perceptual objective in the U-Net embedding space of the diffusion model to address these issues.
  arXiv  Detail & Related papers  (2024-06-25T15:21:50Z)
• Aligning Diffusion Models by Optimizing Human Utility [1.6166249658374658]
  Diffusion-KTO is a novel approach for aligning text-to-image diffusion models with human preferences. Our objective requires simple per-image binary feedback signals, e.g. likes or dislikes, which are abundantly available.
  arXiv  Detail & Related papers  (2024-04-06T01:23:23Z)
• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation [59.184980778643464]
  Fine-tuning Diffusion Models remains an underexplored frontier in generative artificial intelligence (GenAI) In this paper, we introduce an innovative technique called self-play fine-tuning for diffusion models (SPIN-Diffusion) Our approach offers an alternative to conventional supervised fine-tuning and RL strategies, significantly improving both model performance and alignment.
  arXiv  Detail & Related papers  (2024-02-15T18:59:18Z)
• Diffusion Model Alignment Using Direct Preference Optimization [103.2238655827797]
  Diffusion-DPO is a method to align diffusion models to human preferences by directly optimizing on human comparison data. We fine-tune the base model of the state-of-the-art Stable Diffusion XL (SDXL)-1.0 model with Diffusion-DPO. We also develop a variant that uses AI feedback and has comparable performance to training on human preferences.
  arXiv  Detail & Related papers  (2023-11-21T15:24:05Z)
• Are Diffusion Models Vision-And-Language Reasoners? [30.579483430697803]
  We transform diffusion-based models for any image-text matching (ITM) task using a novel method called DiffusionITM. We introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis. We find that Stable Diffusion + DiffusionITM is competitive on many tasks and outperforms CLIP on compositional tasks like CLEVR and Winoground.
  arXiv  Detail & Related papers  (2023-05-25T18:02:22Z)
• LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models [62.75006608940132]
  This work proposes to enhance prompt understanding capabilities in text-to-image diffusion models. Our method leverages a pretrained large language model for grounded generation in a novel two-stage process. Our method significantly outperforms the base diffusion model and several strong baselines in accurately generating images.
  arXiv  Detail & Related papers  (2023-05-23T03:59:06Z)
• Training Diffusion Models with Reinforcement Learning [82.29328477109826]
  Diffusion models are trained with an approximation to the log-likelihood objective. In this paper, we investigate reinforcement learning methods for directly optimizing diffusion models for downstream objectives. We describe how posing denoising as a multi-step decision-making problem enables a class of policy gradient algorithms.
  arXiv  Detail & Related papers  (2023-05-22T17:57:41Z)
• DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models [81.84866217721361]
  DiffusionBERT is a new generative masked language model based on discrete diffusion models. We propose a new noise schedule for the forward diffusion process that controls the degree of noise added at each step. Experiments on unconditional text generation demonstrate that DiffusionBERT achieves significant improvement over existing diffusion models for text.
  arXiv  Detail & Related papers  (2022-11-28T03:25:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.