Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On
- URL: http://arxiv.org/abs/2607.21694v1
- Date: Thu, 23 Jul 2026 17:45:56 GMT
- Title: Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On
- Abstract summary: Oxygen-TryOn is a unified foundation model for any-item virtual try-on.<n>It is built for try-on through a dedicated data engine and try-on-specific training.
- Score: 50.93194436640413
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We present Oxygen-TryOn, a unified foundation model for any-item virtual try-on. Rather than repurposing a general-purpose image editor, Oxygen-TryOn is fashion-native, built for try-on through a dedicated data engine and try-on-specific training. Given one or more reference items (clean product shots or in-the-wild worn-on photos) and a single target subject image, it synthesizes a photorealistic image of the subject wearing the items across virtually any fashion category. Prior systems handle a single garment category in a studio setting, and recent multi-reference methods remain garment-centric; in contrast, Oxygen-TryOn supports diverse items and scenarios, including full- and half-body views, a variable number of references, and free multi-item composition, while faithfully preserving both subject identity and item appearance. Instead of mask-based inpainting, we reformulate try-on as a multi-reference, understanding-driven generation task. We build a data engine that collects, manufactures, annotates, and filters high-quality try-on data at scale, and design a three-stage recipe of continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL). The RL stage uses a hybrid reward combining an in-house try-on reward model with a proprietary, rubric-guided general-purpose model, jointly supervising fine-grained consistency and instruction-level quality. It also follows general editing instructions (e.g., pose changes) in the same pass. Across public benchmarks and our in-house Oxygen-TryOn Bench, it achieves state-of-the-art consistency and realism on single-item try-on and leads on multi-item try-on, matching or surpassing both leading proprietary systems (Nano Banana Pro, GPT-Image-2, Seedream5 Lite) and open-source models (FLUX.2).
Related papers
- UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation [54.38636515750502]
We propose UniLayDiff: a Unified Diffusion Transformer for content-aware layout generation tasks.<n>We employ Multi-Modal Diffusion Transformer framework to capture the complex interplay between the background image, layout elements, and diverse constraints.<n>Experiments demonstrate that UniLayDiff achieves state-of-the-art performance across from unconditional to various conditional generation tasks.
arXiv Detail & Related papers (2025-12-09T18:38:44Z) - OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning [26.133555631867385]
OneReward is a unified reinforcement learning framework that enhances the model's generative capabilities across multiple tasks.<n>We develop Seedream 3.0 Fill, a mask-guided generation model trained via multi-task reinforcement learning.
arXiv Detail & Related papers (2025-08-28T17:59:46Z) - OmniTry: Virtual Try-On Anything without Masks [13.981452272679785]
This paper presents OmniTry, a unified framework that extends Virtual Try-ON (VTON) beyond garment to encompass any wearable objects.<n>Data curation is challenging for obtaining paired images, i.e., the object image and the corresponding try-on result.
arXiv Detail & Related papers (2025-08-19T08:47:31Z) - One Model For All: Partial Diffusion for Unified Try-On and Try-Off in Any Pose [99.056324701764]
We introduce textbfOMFA (emphOne Model For All), a unified diffusion framework for both virtual try-on and try-off.<n>The framework is entirely mask-free and requires only a single portrait and a target pose as input.<n>It achieves state-of-the-art results on both try-on and try-off tasks, providing a practical and generalizable solution for virtual garment synthesis.
arXiv Detail & Related papers (2025-08-06T15:46:01Z) - FashionComposer: Compositional Fashion Image Generation [38.34543351663932]
We present FashionComposer for compositional fashion image generation.<n>It takes multi-modal input (i.e., text prompt, parametric human model, garment image, and face image) and supports personalizing the appearance, pose, and figure of the human.<n>As a comprehensive solution, FashionComposer also supports many other applications like human album generation, diverse virtual try-on tasks, etc.
arXiv Detail & Related papers (2024-12-18T18:59:50Z) - MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation [70.83668869857665]
MMTryon is a multi-modal multi-reference VIrtual Try-ON framework.
It can generate high-quality compositional try-on results by taking a text instruction and multiple garment images as inputs.
arXiv Detail & Related papers (2024-05-01T11:04:22Z) - AnyDoor: Zero-shot Object-level Image Customization [63.44307304097742]
This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations.
Our model is trained only once and effortlessly generalizes to diverse object-scene combinations at the inference stage.
arXiv Detail & Related papers (2023-07-18T17:59:02Z) - Single Stage Virtual Try-on via Deformable Attention Flows [51.70606454288168]
Virtual try-on aims to generate a photo-realistic fitting result given an in-shop garment and a reference person image.
We develop a novel Deformable Attention Flow (DAFlow) which applies the deformable attention scheme to multi-flow estimation.
Our proposed method achieves state-of-the-art performance both qualitatively and quantitatively.
arXiv Detail & Related papers (2022-07-19T10:01:31Z)
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.