Readout Guidance: Learning Control from Diffusion Features

• URL: http://arxiv.org/abs/2312.02150v2
• Date: Tue, 2 Apr 2024 20:12:20 GMT
• Title: Readout Guidance: Learning Control from Diffusion Features
• Authors: Grace Luo, Trevor Darrell, Oliver Wang, Dan B Goldman, Aleksander Holynski,
• Abstract summary: We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen diffusion model at every timestep. These readouts can encode single-image properties, such as pose, depth, and edges; or higher-order properties that relate multiple images, such as correspondence and appearance similarity.
• Score: 96.22155562120231
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen diffusion model at every timestep. These readouts can encode single-image properties, such as pose, depth, and edges; or higher-order properties that relate multiple images, such as correspondence and appearance similarity. Furthermore, by comparing the readout estimates to a user-defined target, and back-propagating the gradient through the readout head, these estimates can be used to guide the sampling process. Compared to prior methods for conditional generation, Readout Guidance requires significantly fewer added parameters and training samples, and offers a convenient and simple recipe for reproducing different forms of conditional control under a single framework, with a single architecture and sampling procedure. We showcase these benefits in the applications of drag-based manipulation, identity-consistent generation, and spatially aligned control. Project page: https://readout-guidance.github.io.

Related papers

• Pre-Trained Vision-Language Models as Partial Annotators [40.89255396643592]
  Pre-trained vision-language models learn massive data to model unified representations of images and natural languages. In this paper, we investigate a novel "pre-trained annotating - weakly-supervised learning" paradigm for pre-trained model application and experiment on image classification tasks.
  arXiv  Detail & Related papers  (2024-05-23T17:17:27Z)
• 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)
• Unleashing Text-to-Image Diffusion Models for Visual Perception [84.41514649568094]
  VPD (Visual Perception with a pre-trained diffusion model) is a new framework that exploits the semantic information of a pre-trained text-to-image diffusion model in visual perception tasks. We show that VPD can be faster adapted to downstream visual perception tasks using the proposed VPD.
  arXiv  Detail & Related papers  (2023-03-03T18:59:47Z)
• Attend to the Right Context: A Plug-and-Play Module for Content-Controllable Summarization [38.894418920684366]
  We propose a plug-and-play module RelAttn to adapt any general summarizers to the content-controllable summarization task. Experiments show that our method effectively improves all the summarizers, and outperforms the prefix-based method and a widely used plug-and-play model.
  arXiv  Detail & Related papers  (2022-12-21T07:17:32Z)
• Self-Guided Diffusion Models [53.825634944114285]
  We propose a framework for self-guided diffusion models. Our method provides guidance signals at various image granularities. Our experiments on single-label and multi-label image datasets demonstrate that self-labeled guidance always outperforms diffusion models without guidance.
  arXiv  Detail & Related papers  (2022-10-12T17:57:58Z)
• clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIP [1.3733526575192976]
  We introduce a new method to efficiently create text-to-image models from a pre-trained CLIP and StyleGAN. It enables text driven sampling with an existing generative model without any external data or fine-tuning. We leverage the alignment between CLIP's image and text embeddings to avoid the need for any text labelled data for training the conditional diffusion model.
  arXiv  Detail & Related papers  (2022-10-05T15:49:41Z)
• More Control for Free! Image Synthesis with Semantic Diffusion Guidance [79.88929906247695]
  Controllable image synthesis models allow creation of diverse images based on text instructions or guidance from an example image. We introduce a novel unified framework for semantic diffusion guidance, which allows either language or image guidance, or both. We conduct experiments on FFHQ and LSUN datasets, and show results on fine-grained text-guided image synthesis.
  arXiv  Detail & Related papers  (2021-12-10T18:55:50Z)
• Diffusion-Based Representation Learning [65.55681678004038]
  We augment the denoising score matching framework to enable representation learning without any supervised signal. In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective. Using the same approach, we propose to learn an infinite-dimensional latent code that achieves improvements of state-of-the-art models on semi-supervised image classification.
  arXiv  Detail & Related papers  (2021-05-29T09:26:02Z)

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.