Sparse Repellency for Shielded Generation in Text-to-image Diffusion Models

• URL: http://arxiv.org/abs/2410.06025v2
• Date: Thu, 10 Oct 2024 17:59:16 GMT
• Title: Sparse Repellency for Shielded Generation in Text-to-image Diffusion Models
• Authors: Michael Kirchhof, James Thornton, Pierre Ablin, Louis Béthune, Eugene Ndiaye, Marco Cuturi,
• Abstract summary: We propose a method that coaxes the sampled trajectories of pretrained diffusion models to land on images that fall outside of a reference set. We achieve this by adding repellency terms to the diffusion SDE throughout the generation trajectory. We show that adding SPELL to popular diffusion models improves their diversity while impacting their FID only marginally, and performs comparatively better than other recent training-free diversity methods.
• Score: 29.083402085790016
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The increased adoption of diffusion models in text-to-image generation has triggered concerns on their reliability. Such models are now closely scrutinized under the lens of various metrics, notably calibration, fairness, or compute efficiency. We focus in this work on two issues that arise when deploying these models: a lack of diversity when prompting images, and a tendency to recreate images from the training set. To solve both problems, we propose a method that coaxes the sampled trajectories of pretrained diffusion models to land on images that fall outside of a reference set. We achieve this by adding repellency terms to the diffusion SDE throughout the generation trajectory, which are triggered whenever the path is expected to land too closely to an image in the shielded reference set. Our method is sparse in the sense that these repellency terms are zero and inactive most of the time, and even more so towards the end of the generation trajectory. Our method, named SPELL for sparse repellency, can be used either with a static reference set that contains protected images, or dynamically, by updating the set at each timestep with the expected images concurrently generated within a batch. We show that adding SPELL to popular diffusion models improves their diversity while impacting their FID only marginally, and performs comparatively better than other recent training-free diversity methods. We also demonstrate how SPELL can ensure a shielded generation away from a very large set of protected images by considering all 1.2M images from ImageNet as the protected set.

Related papers

• MMAR: Towards Lossless Multi-Modal Auto-Regressive Probabilistic Modeling [64.09238330331195]
  We propose a novel Multi-Modal Auto-Regressive (MMAR) probabilistic modeling framework. Unlike discretization line of method, MMAR takes in continuous-valued image tokens to avoid information loss. We show that MMAR demonstrates much more superior performance than other joint multi-modal models.
  arXiv  Detail & Related papers  (2024-10-14T17:57:18Z)
• DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling [6.7206291284535125]
  We present an effective data augmentation framework leveraging the Large Language Model (LLM) and Diffusion Model (DM) Our approach addresses the issue of increasing the diversity of synthetic images. Our method produces synthetic images with enhanced diversity while maintaining adherence to the target distribution.
  arXiv  Detail & Related papers  (2024-09-25T14:02:43Z)
• DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models [18.938687631109925]
  Diffusion-based personalized visual content generation technologies have achieved significant breakthroughs. However, when misused to fabricate fake news or unsettling content targeting individuals, these technologies could cause considerable societal harm. This paper introduces a novel Dual-Domain Anti-Personalization framework (DDAP) By alternating between these two methods, we construct the DDAP framework, effectively harnessing the strengths of both domains.
  arXiv  Detail & Related papers  (2024-07-29T16:11:21Z)
• Direct Consistency Optimization for Compositional Text-to-Image Personalization [73.94505688626651]
  Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, are able to generate visuals with a high degree of consistency. We propose to fine-tune the T2I model by maximizing consistency to reference images, while penalizing the deviation from the pretrained model.
  arXiv  Detail & Related papers  (2024-02-19T09:52:41Z)
• 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)
• 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)
• ADIR: Adaptive Diffusion for Image Reconstruction [46.838084286784195]
  We propose a conditional sampling scheme that exploits the prior learned by diffusion models. We then combine it with a novel approach for adapting pretrained diffusion denoising networks to their input. We show that our proposed adaptive diffusion for image reconstruction' approach achieves a significant improvement in the super-resolution, deblurring, and text-based editing tasks.
  arXiv  Detail & Related papers  (2022-12-06T18:39:58Z)
• SinDiffusion: Learning a Diffusion Model from a Single Natural Image [159.4285444680301]
  We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image. It is based on two core designs. First, SinDiffusion is trained with a single model at a single scale instead of multiple models with progressive growing of scales. Second, we identify that a patch-level receptive field of the diffusion network is crucial and effective for capturing the image's patch statistics.
  arXiv  Detail & Related papers  (2022-11-22T18:00:03Z)
• Conffusion: Confidence Intervals for Diffusion Models [32.36217153362305]
  Current diffusion-based methods do not provide statistical guarantees regarding the generated results. We propose Conffusion, wherein we fine-tune a pre-trained diffusion model to predict interval bounds in a single forward pass. We show that Conffusion outperforms the baseline method while being three orders of magnitude faster.
  arXiv  Detail & Related papers  (2022-11-17T18:58:15Z)
• Lafite2: Few-shot Text-to-Image Generation [132.14211027057766]
  We propose a novel method for pre-training text-to-image generation model on image-only datasets. It considers a retrieval-then-optimization procedure to synthesize pseudo text features. It can be beneficial to a wide range of settings, including the few-shot, semi-supervised and fully-supervised learning.
  arXiv  Detail & Related papers  (2022-10-25T16:22:23Z)

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.