Improving GFlowNets for Text-to-Image Diffusion Alignment

• URL: http://arxiv.org/abs/2406.00633v2
• Date: Sun, 16 Jun 2024 20:45:19 GMT
• Title: Improving GFlowNets for Text-to-Image Diffusion Alignment
• Authors: Dinghuai Zhang, Yizhe Zhang, Jiatao Gu, Ruixiang Zhang, Josh Susskind, Navdeep Jaitly, Shuangfei Zhai,
• Abstract summary: 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.
• Score: 48.42367859859971
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as alignment to a text description, which can be specified with a black-box reward function. Prior works fine-tune pretrained diffusion models to achieve this goal through reinforcement learning-based algorithms. Nonetheless, they suffer from issues including slow credit assignment as well as low quality in their generated samples. In this work, we explore techniques that do not directly maximize the reward but rather generate high-reward images with relatively high probability -- a natural scenario for the framework of generative flow networks (GFlowNets). To this end, we propose the Diffusion Alignment with GFlowNet (DAG) algorithm to post-train diffusion models with black-box property functions. Extensive experiments on Stable Diffusion and various reward specifications corroborate that our method could effectively align large-scale text-to-image diffusion models with given reward information.

Related papers

• FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models [56.71672127740099]
  We focus on the task of image segmentation, which is traditionally solved by training models on closed-vocabulary datasets. We leverage different and relatively small-sized, open-source foundation models for zero-shot open-vocabulary segmentation. Our approach (dubbed FreeSeg-Diff), which does not rely on any training, outperforms many training-based approaches on both Pascal VOC and COCO datasets.
  arXiv  Detail & Related papers  (2024-03-29T10:38:25Z)
• 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)
• The Journey, Not the Destination: How Data Guides Diffusion Models [75.19694584942623]
  Diffusion models trained on large datasets can synthesize photo-realistic images of remarkable quality and diversity. We propose a framework that: (i) provides a formal notion of data attribution in the context of diffusion models, and (ii) allows us to counterfactually validate such attributions.
  arXiv  Detail & Related papers  (2023-12-11T08:39:43Z)
• Aligning Text-to-Image Diffusion Models with Reward Backpropagation [62.45086888512723]
  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.
  arXiv  Detail & Related papers  (2023-10-05T17:59:18Z)
• Steered Diffusion: A Generalized Framework for Plug-and-Play Conditional Image Synthesis [62.07413805483241]
  Steered Diffusion is a framework for zero-shot conditional image generation using a diffusion model trained for unconditional generation. We present experiments using steered diffusion on several tasks including inpainting, colorization, text-guided semantic editing, and image super-resolution.
  arXiv  Detail & Related papers  (2023-09-30T02:03:22Z)
• Reverse Stable Diffusion: What prompt was used to generate this image? [73.10116197883303]
  We study the task of predicting the prompt embedding given an image generated by a generative diffusion model. We propose a novel learning framework comprising a joint prompt regression and multi-label vocabulary classification objective. We conduct experiments on the DiffusionDB data set, predicting text prompts from images generated by Stable Diffusion.
  arXiv  Detail & Related papers  (2023-08-02T23:39:29Z)
• Flow Matching in Latent Space [2.9330609943398525]
  Flow matching is a framework to train generative models that exhibits impressive empirical performance. We propose to apply flow matching in the latent spaces of pretrained autoencoders, which offers improved computational efficiency. Our work stands as a pioneering contribution in the integration of various conditions into flow matching for conditional generation tasks.
  arXiv  Detail & Related papers  (2023-07-17T17:57:56Z)
• Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation [11.80682025950519]
  In this work, we investigate the diffusion (physics) in diffusion (machine learning) properties. We propose our Cyclic One-Way Diffusion (COW) method to control the direction of diffusion phenomenon. Our method provides a novel perspective to understand the task needs and is applicable to a wider range of customization scenarios.
  arXiv  Detail & Related papers  (2023-06-14T05:25:06Z)

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.