Aligning Text-to-Image Diffusion Models with Reward Backpropagation

• URL: http://arxiv.org/abs/2310.03739v5
• Date: Thu, 07 Nov 2024 03:54:22 GMT
• Title: Aligning Text-to-Image Diffusion Models with Reward Backpropagation
• Authors: Mihir Prabhudesai, Anirudh Goyal, Deepak Pathak, Katerina Fragkiadaki,
• Abstract summary: We propose AlignProp, a method that aligns diffusion models to downstream reward functions using end-to-end backpropagation of the reward gradient. We show AlignProp achieves higher rewards in fewer training steps than alternatives, while being conceptually simpler.
• Score: 62.45086888512723
• License:
• Abstract: Text-to-image diffusion models have recently emerged at the forefront of image generation, powered by very large-scale unsupervised or weakly supervised text-to-image training datasets. Due to their unsupervised training, controlling their behavior in downstream tasks, such as maximizing human-perceived image quality, image-text alignment, or ethical image generation, is difficult. Recent works finetune diffusion models to downstream reward functions using vanilla reinforcement learning, notorious for the high variance of the gradient estimators. In this paper, we propose AlignProp, a method that aligns diffusion models to downstream reward functions using end-to-end backpropagation of the reward gradient through the denoising process. While naive implementation of such backpropagation would require prohibitive memory resources for storing the partial derivatives of modern text-to-image models, AlignProp finetunes low-rank adapter weight modules and uses gradient checkpointing, to render its memory usage viable. We test AlignProp in finetuning diffusion models to various objectives, such as image-text semantic alignment, aesthetics, compressibility and controllability of the number of objects present, as well as their combinations. We show AlignProp achieves higher rewards in fewer training steps than alternatives, while being conceptually simpler, making it a straightforward choice for optimizing diffusion models for differentiable reward functions of interest. Code and Visualization results are available at https://align-prop.github.io/.

Related papers

• PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference [62.72779589895124]
  We make the first attempt to align diffusion models for image inpainting with human aesthetic standards via a reinforcement learning framework. We train a reward model with a dataset we construct, consisting of nearly 51,000 images annotated with human preferences. Experiments on inpainting comparison and downstream tasks, such as image extension and 3D reconstruction, demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2024-10-29T11:49:39Z)
• Improving GFlowNets for Text-to-Image Diffusion Alignment [48.42367859859971]
  We explore techniques that do not directly maximize the reward but rather generate high-reward images with relatively high probability. Our method could effectively align large-scale text-to-image diffusion models with given reward information.
  arXiv  Detail & Related papers  (2024-06-02T06:36:46Z)
• Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models [23.786473791344395]
  Cross-attention layers in diffusion models tend to disproportionately focus on certain tokens during the generation process. We introduce attention regulation, an on-the-fly optimization approach at inference time to align attention maps with the input text prompt. Experiment results show that our method consistently outperforms other baselines.
  arXiv  Detail & Related papers  (2024-03-11T02:18:27Z)
• Reinforcement Learning from Diffusion Feedback: Q* for Image Search [2.5835347022640254]
  We present two models for image generation using model-agnostic learning. RLDF is a singular approach for visual imitation through prior-preserving reward function guidance. It generates high-quality images over varied domains showcasing class-consistency and strong visual diversity.
  arXiv  Detail & Related papers  (2023-11-27T09:20:12Z)
• DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models [97.31200133440308]
  We propose using online reinforcement learning to fine-tune text-to-image models. We focus on diffusion models, defining the fine-tuning task as an RL problem. Our approach, coined DPOK, integrates policy optimization with KL regularization.
  arXiv  Detail & Related papers  (2023-05-25T17:35:38Z)
• Generating images of rare concepts using pre-trained diffusion models [32.5337654536764]
  Text-to-image diffusion models can synthesize high-quality images, but they have various limitations. We show that their limitation is partly due to the long-tail nature of their training data. We show that rare concepts can be correctly generated by carefully selecting suitable generation seeds in the noise space.
  arXiv  Detail & Related papers  (2023-04-27T20:55:38Z)
• Masked Images Are Counterfactual Samples for Robust Fine-tuning [77.82348472169335]
  Fine-tuning deep learning models can lead to a trade-off between in-distribution (ID) performance and out-of-distribution (OOD) robustness. We propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
  arXiv  Detail & Related papers  (2023-03-06T11:51:28Z)
• Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models [60.63556257324894]
  A key desired property of image generative models is the ability to disentangle different attributes. We propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation. Experiments show that the proposed method can modify a wide range of attributes, with the performance outperforming diffusion-model-based image-editing algorithms.
  arXiv  Detail & Related papers  (2022-12-16T19:58:52Z)

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.