Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

Hugging Face Daily Papers Papers

Summary

Introduces appearance pointers, compact tokens that guide Diffusion Transformers to apply correct appearance cues at specified spatial locations, enabling modality-agnostic localized multimodal control without retraining the base model.

Controllable image generation remains challenging for creative professionals, who often require precise regional control over materials, object identities, and spatial arrangements that cannot be reliably achieved through text prompting alone. Diffusion Transformers (DiTs) can natively ingest heterogeneous tokens stemming from texts and images, but they lack mechanisms for determining where and how these tokens should influence the output. We introduce appearance pointers, compact tokens that guide DiTs toward the correct appearance cues at the correct spatial locations by aligning text or image inputs with user-specified masks. Appearance pointers are produced by a region correspondence network and refined through a spatial aggregation mechanism, enabling the model to handle multiple regional descriptions without significantly increasing token load. Our approach introduces the first modality-agnostic interface for localized multimodal control in a DiT without retraining the base model from scratch. Across a range of metrics, our single model reaches or surpasses the performance of modality-specific state of the art methods, offering a simple and extensible path toward precise, region-aware, multimodal guidance in generative image synthesis.
Original Article
View Cached Full Text

Cached at: 07/22/26, 02:40 AM

Paper page - Appearance Pointers – Multimodal Region Control of Diffusion Transformers

Source: https://huggingface.co/papers/2607.19344

Abstract

Controllableimagegenerationremainschallengingforcreativeprofessionals,whooftenrequirepreciseregionalcontrolovermaterials,objectidentities,andspatialarrangementsthatcannotbereliablyachievedthroughtextpromptingalone.DiffusionTransformers(DiTs)cannativelyingestheterogeneoustokensstemmingfromtextsandimages,buttheylackmechanismsfordeterminingwhereandhowthesetokensshouldinfluencetheoutput.Weintroduceappearancepointers,compacttokensthatguideDiTstowardthecorrectappearancecuesatthecorrectspatiallocationsbyaligningtextorimageinputswithuser-specifiedmasks.Appearancepointersareproducedbyaregioncorrespondencenetworkandrefinedthroughaspatialaggregationmechanism,enablingthemodeltohandlemultipleregionaldescriptionswithoutsignificantlyincreasingtokenload.Ourapproachintroducesthefirstmodality-agnosticinterfaceforlocalizedmultimodalcontrolinaDiTwithoutretrainingthebasemodelfromscratch.Acrossarangeofmetrics,oursinglemodelreachesorsurpassestheperformanceofmodality-specificstateoftheartmethods,offeringasimpleandextensiblepathtowardprecise,region-aware,multimodalguidanceingenerativeimagesynthesis.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.19344

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.19344 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.19344 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.19344 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Hugging Face Daily Papers

PerceptionDLM introduces a multimodal diffusion language model that enables parallel region perception via structured attention masking and efficient prompting, achieving faster inference without sacrificing caption quality. Experiments show competitive performance with substantial speed improvements for multi-region perception tasks.

Registers Matter for Pixel-Space Diffusion Transformers

Hugging Face Daily Papers

This paper explores the use of register tokens in pixel-space Diffusion Transformers (DiTs), finding they improve feature map quality despite DiTs lacking patch-token outliers. The authors propose Register Guidance, a technique to amplify register contributions for better visual structure.