FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers

• URL: http://arxiv.org/abs/2412.09611v1
• Date: Thu, 12 Dec 2024 18:59:40 GMT
• Title: FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers
• Authors: Yusuf Dalva, Kavana Venkatesh, Pinar Yanardag,
• Abstract summary: We introduce FluxSpace, a domain-agnostic image editing method with the ability to control the semantics of images generated by rectified flow transformers. By leveraging the representations learned by the transformer blocks within the rectified flow models, we propose a set of semantically interpretable representations that enable a wide range of image editing tasks.
• Score: 4.710921988115686
• License:
• Abstract: Rectified flow models have emerged as a dominant approach in image generation, showcasing impressive capabilities in high-quality image synthesis. However, despite their effectiveness in visual generation, rectified flow models often struggle with disentangled editing of images. This limitation prevents the ability to perform precise, attribute-specific modifications without affecting unrelated aspects of the image. In this paper, we introduce FluxSpace, a domain-agnostic image editing method leveraging a representation space with the ability to control the semantics of images generated by rectified flow transformers, such as Flux. By leveraging the representations learned by the transformer blocks within the rectified flow models, we propose a set of semantically interpretable representations that enable a wide range of image editing tasks, from fine-grained image editing to artistic creation. This work offers a scalable and effective image editing approach, along with its disentanglement capabilities.

Related papers

• Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing [43.97960454977206]
  In this paper, we analyze the diffusion inversion and invariance control based on the flow transformer. We propose a two-stage inversion to first refine the velocity estimation and then compensate for the leftover error. This mechanism can simultaneously preserve the non-target contents while allowing rigid and non-rigid manipulation.
  arXiv  Detail & Related papers  (2024-11-24T13:48:16Z)
• Stable Flow: Vital Layers for Training-Free Image Editing [74.52248787189302]
  Diffusion models have revolutionized the field of content synthesis and editing. Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT) We propose an automatic method to identify "vital layers" within DiT, crucial for image formation. Next, to enable real-image editing, we introduce an improved image inversion method for flow models.
  arXiv  Detail & Related papers  (2024-11-21T18:59:51Z)
• Streamlining Image Editing with Layered Diffusion Brushes [8.738398948669609]
  Our system renders a single edit on a 512x512 image within 140 ms using a high-end consumer GPU. Our approach demonstrates efficacy across a range of tasks, including object attribute adjustments, error correction, and sequential prompt-based object placement and manipulation.
  arXiv  Detail & Related papers  (2024-05-01T04:30:03Z)
• Editable Image Elements for Controllable Synthesis [79.58148778509769]
  We propose an image representation that promotes spatial editing of input images using a diffusion model. We show the effectiveness of our representation on various image editing tasks, such as object resizing, rearrangement, dragging, de-occlusion, removal, variation, and image composition.
  arXiv  Detail & Related papers  (2024-04-24T17:59:11Z)
• Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators [19.853978560075305]
  Motion guidance is a technique that allows a user to specify dense, complex motion fields that indicate where each pixel in an image should move. We demonstrate that our technique works on complex motions and produces high quality edits of real and generated images.
  arXiv  Detail & Related papers  (2024-01-31T18:59:59Z)
• Latent Space Editing in Transformer-Based Flow Matching [53.75073756305241]
  Flow Matching with a transformer backbone offers the potential for scalable and high-quality generative modeling. We introduce an editing space, $u$-space, that can be manipulated in a controllable, accumulative, and composable manner. Lastly, we put forth a straightforward yet powerful method for achieving fine-grained and nuanced editing using text prompts.
  arXiv  Detail & Related papers  (2023-12-17T21:49:59Z)
• LayerDiffusion: Layered Controlled Image Editing with Diffusion Models [5.58892860792971]
  LayerDiffusion is a semantic-based layered controlled image editing method. We leverage a large-scale text-to-image model and employ a layered controlled optimization strategy. Experimental results demonstrate the effectiveness of our method in generating highly coherent images.
  arXiv  Detail & Related papers  (2023-05-30T01:26:41Z)
• The Stable Artist: Steering Semantics in Diffusion Latent Space [17.119616029527744]
  We present the Stable Artist, an image editing approach enabling fine-grained control of the image generation process. The main component is semantic guidance (SEGA) which steers the diffusion process along variable numbers of semantic directions. SEGA enables probing of latent spaces to gain insights into the representation of concepts learned by the model.
  arXiv  Detail & Related papers  (2022-12-12T16:21:24Z)
• DiffEdit: Diffusion-based semantic image editing with mask guidance [64.555930158319]
  DiffEdit is a method to take advantage of text-conditioned diffusion models for the task of semantic image editing. Our main contribution is able to automatically generate a mask highlighting regions of the input image that need to be edited.
  arXiv  Detail & Related papers  (2022-10-20T17:16:37Z)
• Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation [136.53288628437355]
  Controllable semantic image editing enables a user to change entire image attributes with few clicks. Current approaches often suffer from attribute edits that are entangled, global image identity changes, and diminished photo-realism. We propose quantitative evaluation strategies for measuring controllable editing performance, unlike prior work which primarily focuses on qualitative evaluation.
  arXiv  Detail & Related papers  (2021-02-01T21:38:36Z)
• Look here! A parametric learning based approach to redirect visual attention [49.609412873346386]
  We introduce an automatic method to make an image region more attention-capturing via subtle image edits. Our model predicts a distinct set of global parametric transformations to be applied to the foreground and background image regions. Our edits enable inference at interactive rates on any image size, and easily generalize to videos.
  arXiv  Detail & Related papers  (2020-08-12T16:08:36Z)

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.