RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance

• URL: http://arxiv.org/abs/2405.17661v1
• Date: Mon, 27 May 2024 21:23:20 GMT
• Title: RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
• Authors: Jiaojiao Fan, Haotian Xue, Qinsheng Zhang, Yongxin Chen,
• Abstract summary: RefDrop allows users to control the influence of reference context in a direct and precise manner. Our method also enables more interesting applications, such as the consistent generation of multiple subjects.
• Score: 22.326405355520176
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from multiple reference images provides an efficient approach to enhancing consistency without fine-tuning. Despite its popularity and success, few studies have elucidated the underlying mechanisms that contribute to its effectiveness. In this work, we reveal that the popular approach is a linear interpolation of image self-attention and cross-attention between synthesized content and reference features, with a constant rank-1 coefficient. Motivated by this observation, we find that a rank-1 coefficient is not necessary and simplifies the controllable generation mechanism. The resulting algorithm, which we coin as RefDrop, allows users to control the influence of reference context in a direct and precise manner. Besides further enhancing consistency in single-subject image generation, our method also enables more interesting applications, such as the consistent generation of multiple subjects, suppressing specific features to encourage more diverse content, and high-quality personalized video generation by boosting temporal consistency. Even compared with state-of-the-art image-prompt-based generators, such as IP-Adapter, RefDrop is competitive in terms of controllability and quality while avoiding the need to train a separate image encoder for feature injection from reference images, making it a versatile plug-and-play solution for any image or video diffusion model.

Related papers

• A Simple Approach to Unifying Diffusion-based Conditional Generation [63.389616350290595]
  We introduce a simple, unified framework to handle diverse conditional generation tasks. Our approach enables versatile capabilities via different inference-time sampling schemes. Our model supports additional capabilities like non-spatially aligned and coarse conditioning.
  arXiv  Detail & Related papers  (2024-10-15T09:41:43Z)
• ZePo: Zero-Shot Portrait Stylization with Faster Sampling [61.14140480095604]
  This paper presents an inversion-free portrait stylization framework based on diffusion models that accomplishes content and style feature fusion in merely four sampling steps. We propose a feature merging strategy to amalgamate redundant features in Consistency Features, thereby reducing the computational load of attention control.
  arXiv  Detail & Related papers  (2024-08-10T08:53:41Z)
• FilterPrompt: Guiding Image Transfer in Diffusion Models [9.386850486378382]
  FilterPrompt is an approach to enhance the model control effect. It can be universally applied to any diffusion model, allowing users to adjust the representation of specific image features.
  arXiv  Detail & Related papers  (2024-04-20T04:17:34Z)
• LCM-Lookahead for Encoder-based Text-to-Image Personalization [82.56471486184252]
  We explore the potential of using shortcut-mechanisms to guide the personalization of text-to-image models. We focus on encoder-based personalization approaches, and demonstrate that by tuning them with a lookahead identity loss, we can achieve higher identity fidelity.
  arXiv  Detail & Related papers  (2024-04-04T17:43:06Z)
• MM-Diff: High-Fidelity Image Personalization via Multi-Modal Condition Integration [7.087475633143941]
  MM-Diff is a tuning-free image personalization framework capable of generating high-fidelity images of both single and multiple subjects in seconds. MM-Diff employs a vision encoder to transform the input image into CLS and patch embeddings. CLS embeddings are used on the one hand to augment the text embeddings, and on the other hand together with patch embeddings to derive a small number of detail-rich subject embeddings.
  arXiv  Detail & Related papers  (2024-03-22T09:32:31Z)
• DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance [69.0740091741732]
  We propose a high-fidelity image-to-video generation method by devising a frame retention branch based on a pre-trained video diffusion model, named DreamVideo. Our model has a powerful image retention ability and delivers the best results in UCF101 compared to other image-to-video models to our best knowledge.
  arXiv  Detail & Related papers  (2023-12-05T03:16:31Z)
• DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing [94.24479528298252]
  DragGAN is an interactive point-based image editing framework that achieves impressive editing results with pixel-level precision. By harnessing large-scale pretrained diffusion models, we greatly enhance the applicability of interactive point-based editing on both real and diffusion-generated images. We present a challenging benchmark dataset called DragBench to evaluate the performance of interactive point-based image editing methods.
  arXiv  Detail & Related papers  (2023-06-26T06:04:09Z)
• Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network [92.01145655155374]
  We present an unsupervised image enhancement generative network (UEGAN) It learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner. Results show that the proposed model effectively improves the aesthetic quality of images.
  arXiv  Detail & Related papers  (2020-12-30T03:22:46Z)
• DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation [8.26410341981427]
  The Dual Attention Generative Adversarial Network (DTGAN) can synthesize high-quality and semantically consistent images. The proposed model introduces channel-aware and pixel-aware attention modules that can guide the generator to focus on text-relevant channels and pixels. A new type of visual loss is utilized to enhance the image resolution by ensuring vivid shape and perceptually uniform color distributions of generated images.
  arXiv  Detail & Related papers  (2020-11-05T08:57:15Z)

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.