MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer

• URL: http://arxiv.org/abs/2607.20924v1
• Date: Thu, 23 Jul 2026 05:00:14 GMT
• Title: MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer
• Abstract summary: We propose MagicMakeup, a diffusion transformer-based framework for region-controllable and high-fidelity makeup transfer.<n>We show that MagicMakeup improves regional controllability, makeup fidelity, and identity preservation, with strong robustness across styles, races, and poses.
• Score: 29.344888414711175
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Makeup-transfer applies the reference makeup to the source face while preserving the source identity. Despite advances in full-face editing by diffusion-based methods, strong regional controllability, makeup fidelity, and identity preservation remain challenging. The reasons are (i) pixel-to-attention misalignment that causes spillover into non-target areas and weakens regional control; (ii) unclear transfer/preservation concept separation under two-image conditioning, leading to coupling between makeup attributes and identity; and (iii) the lack of a high-resolution dataset that is identity-consistent and region-labeled for fine-grained supervision. In this paper, we propose MagicMakeup, a diffusion transformer-based framework for region-controllable and high-fidelity makeup transfer, built on spatial constraints and concept disentanglement. To enable precise region-specific editing while preserving identity, we propose Token-Aligned Region Gating, which aligns pixel masks with attention and applies region-specific logit gating. To clarify the concepts of transfer and preservation, we further introduce Cross-Modal Perception Guidance, which aligns text and image features to enhance cross-modal concept perception. We also design a pipeline for the generation of 1024 x 1024 data pairs through region-specific makeup removal and establish a unified benchmark in synthetic and real settings. Extensive quantitative and qualitative experiments show that MagicMakeup improves regional controllability, makeup fidelity, and identity preservation, with strong robustness across styles, races, and poses.

Related papers

• Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer [70.44549081321442]
  Makeup transfer applies a reference cosmetic style to a source face while preserving its identity and geometry.<n>Current methods rely on weak priors or synthetic pseudo-targets from large-scale editing models.<n>We propose Anchoring on Reality Makeup Transfer (ART), a two-stage framework with a reality-anchored refinement cycle.
  arXiv  Detail & Related papers  (2026-06-30T03:28:01Z)
• In-context Region-based Drag: Drag Any Region to Any Shape [58.32054552329584]
  This paper focuses on region-based drag and introduces a novel In-Context Region-based Drag (ICRDrag) method.<n>Under the in-context learning framework, ICRDrag consumes a source image, a source region mask, and a target region mask, producing the target dragged image.<n>Experiments show that ICRDrag significantly outperforms existing methods in both quantitative metrics and user studies.
  arXiv  Detail & Related papers  (2026-06-24T14:55:07Z)
• CA-IDD: Cross-Attention Guided Identity-Conditional Diffusion for Identity-Consistent Face Swapping [1.4323566945483497]
  Face swapping aims to optimize realistic facial image generation by leveraging the identity of a source face onto a target face.<n>Existing methods, especially GAN-based methods, often struggle to balance identity preservation and visual realism.<n>We introduce CA-IDD, the first diffusion-based face swapping approach that integrates gaze, identity, and facial parsing.
  arXiv  Detail & Related papers  (2026-04-27T13:59:08Z)
• Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers [49.08465459791972]
  Region-instructed layout control in text-to-image generation is highly practical, yet existing methods suffer from limitations.<n>By modeling regional generation as distinct layers and binding them during the generation, we propose LayerBind.
  arXiv  Detail & Related papers  (2026-03-06T00:09:49Z)
• Supervised makeup transfer with a curated dataset: Decoupling identity and makeup features for enhanced transformation [21.71636658071446]
  Diffusion models have shown strong progress in generative tasks, offering a more stable alternative to GAN-based approaches for makeup transfer.<n>Existing methods often suffer from limited datasets, poor disentanglement between identity and makeup features, and weak controllability.<n>We construct a curated high-quality dataset using a train-generate-filter-retrain strategy that combines synthetic, realistic, and filtered samples to improve diversity and fidelity.<n>Third, we propose a text-guided mechanism that allows fine-grained and region-specific control, enabling users to modify eyes, lips, or face makeup with natural language prompts.
  arXiv  Detail & Related papers  (2026-01-31T13:46:38Z)
• FLUX-Makeup: High-Fidelity, Identity-Consistent, and Robust Makeup Transfer via Diffusion Transformer [20.199540657879037]
  We propose FLUX-Makeup, a high-fidelity, identity-consistent, and robust makeup transfer framework.<n>Our method directly leverages source-reference image pairs to achieve superior transfer performance.<n>FLUX-Makeup achieves state-of-the-art performance, exhibiting strong robustness across diverse scenarios.
  arXiv  Detail & Related papers  (2025-08-07T06:42:40Z)
• AvatarMakeup: Realistic Makeup Transfer for 3D Animatable Head Avatars [89.31582684550723]
  AvatarMakeup achieves state-of-the-art makeup transfer quality and consistency throughout animation.<n>Coherent Duplication optimize a global UV map by recoding the averaged facial attributes among the generated makeup images.<n>Experiments demonstrate that AvatarMakeup achieves state-of-the-art makeup transfer quality and consistency throughout animation.
  arXiv  Detail & Related papers  (2025-07-03T08:26:57Z)
• SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization [67.90315365909244]
  We propose a novel Spatial Alignment and Region-Adaptive normalization method (SARA) in this paper. Our method generates detailed makeup transfer results that can handle large spatial misalignments and achieve part-specific and shade-controllable makeup transfer. Experimental results show that our SARA method outperforms existing methods and achieves state-of-the-art performance on two public datasets.
  arXiv  Detail & Related papers  (2023-11-28T14:46:51Z)
• BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer [73.39598356799974]
  We propose a Robust, Efficient, and Component-specific makeup transfer method (abbreviated as BeautyREC) A component-specific correspondence to directly transfer the makeup style of a reference image to the corresponding components. As an auxiliary, the long-range visual dependencies of Transformer are introduced for effective global makeup transfer.
  arXiv  Detail & Related papers  (2022-12-12T12:38:27Z)
• EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer [13.304362849679391]
  We propose Exquisite and locally editable GAN for makeup transfer (EleGANt) It encodes facial attributes into pyramidal feature maps to preserves high-frequency information. EleGANt is the first to achieve customized local editing within arbitrary areas by corresponding editing on the feature maps.
  arXiv  Detail & Related papers  (2022-07-20T11:52:07Z)
• DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis [25.936764522125703]
  We propose a novel normalization module, named Detailed Region-Adaptive Normalization(DRAN) It adaptively learns both fine-grained and coarse-grained style representations. We collect a new makeup dataset (Makeup-Complex dataset) that contains a wide range of complex makeup styles.
  arXiv  Detail & Related papers  (2021-09-29T16:19:37Z)

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.