pith. machine review for the scientific record. sign in

arxiv: 2605.10127 · v2 · submitted 2026-05-11 · 💻 cs.CV

Recognition: 2 theorem links

· Lean Theorem

Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition

Yu He , Ting Zhu , Yichun Liu , Lichen Ma , Xinyuan Shan , Jingling Fu , Yu Shi , Junshi Huang
show 1 more author
Yan Li
Authors on Pith no claims yet

Pith reviewed 2026-05-14 21:52 UTC · model grok-4.3

classification 💻 cs.CV
keywords Fashion130Koutfit generationmulti-modal promptsFusion Transformervisual consistencye-commerce datasetgenerative modelsprompt alignment
0
0 comments X

The pith

Fashion130K dataset and UMC framework align text and image prompts to generate more consistent outfits.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces Fashion130K, a new e-commerce dataset of 130,000 fashion images spanning various occasions, models, and garment types. It proposes the Unified Multi-modal Condition framework that combines text prompts with reference images for outfit generation. An embedding refiner extracts unified embeddings while a Fusion Transformer aligns the text and image modalities by adjusting their gap. The generation model's attention is then modified so the noise image focuses on pivotal prompt tokens. This setup targets the common problem of visual mismatches when mixing modalities, offering a practical path to more reliable clothing generation for design and retail tools.

Core claim

The authors present Fashion130K as a comprehensive dataset and the UMC framework, where an embedding refiner extracts unified embeddings from multi-modal prompts and a Fusion Transformer aligns text and image embeddings by closing the modality gap. The generation model's attention is redesigned to let the noise image select pivotal tokens from these unified prompts, resulting in more consistent garment generation compared to state-of-the-art methods on both the dataset and real-world applications.

What carries the argument

Unified Multi-modal Condition (UMC) with embedding refiner and Fusion Transformer, which aligns text and image embeddings to enable consistent outfit generation.

If this is right

  • Generation models produce outfits with higher visual consistency when using aligned multi-modal embeddings.
  • E-commerce tools gain improved results for design tasks that combine text descriptions and reference photos.
  • Redesigned attention lets noise images prioritize key tokens from prompts during the generation process.
  • Large datasets like Fashion130K support detailed testing of multi-modal conditions beyond single-modality setups.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The alignment approach could extend to other domains like furniture or product visualization where text and images are mixed.
  • If the gap closure works without information loss, separate text-only or image-only models may become less necessary for fashion tasks.
  • Real-world testing with unusual garment combinations would show whether the consistency gains hold for edge cases.

Load-bearing premise

The Fusion Transformer can reliably close the modality gap between text and image embeddings while preserving the information needed for consistent garment generation.

What would settle it

Generate outfits from paired text and image prompts that specify conflicting details such as color or style, then check whether UMC outputs match both inputs more accurately than baseline methods across a held-out test set.

Figures

Figures reproduced from arXiv: 2605.10127 by Jingling Fu, Junshi Huang, Lichen Ma, Ting Zhu, Xinyuan Shan, Yan Li, Yichun Liu, Yu He, Yu Shi.

Figure 1
Figure 1. Figure 1: Our UMC model enables fashion outfit generation with [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Category distribution and visual examples from the [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Overview of the UMC framework, which integrates a multi-modal Embedding Refiner and Selective Attention. We explore [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Impact of different architectural choices on validation [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 6
Figure 6. Figure 6: Visualization of Top-k (k = 8) Attention between noise tokens and multi-modal condition tokens. Compared Methods. We evaluate our method on the test set of Fashion130K, which contains 3000 garment-model pairs with rich captions. Our evaluation covers three cat￾egories of controllable image generation methods: fash￾ion outfit methods (Magic Clothing [5], Any2AnyTryon [11]); subject-driven methods (OmniContr… view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative results compared with various methods for fashion outfit generation on the test set of Fashion130K [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
read the original abstract

Recent research work on fashion outfit generation focuses on promoting visual consistency of garments by leveraging key information from reference image and text prompt. However, the potential of outfit generation remains underexplored, requiring comprehensive e-commercial dataset and elaborative utilization of multi-modal condition. In this paper, we propose a brand-new e-commerce dataset, named Fashion130k, with various occasions, models, and garment types. For the consistent generation of garment, we design a framework with Unified Multi-modal Condition (UMC) to align and integrate the text and visual prompts into generation model. Specifically, we explore an embedding refiner to extract the unified embeddings of multi-modal prompts, within which a Fusion Transformer is proposed to align the multi-modal embeddings by adjusting the modality gap between text and image. Based on unified embeddings, the attention in generation model is redesigned to emphasis the correlations between prompts and noise image, inducing that the noise image can select the pivotal tokens of prompts for consistent outfit generation. Our dataset and proposed framework offer a general and nuanced exploration of multi-modal prompts for generation models. Extensive experiments on real-world applications and benchmark demonstrate the effectiveness of UMC in visual consistency, achieving promising result than that of SoTA methods.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript introduces the Fashion130K dataset, a large-scale e-commerce fashion collection covering diverse occasions, models, and garment types. It proposes a Unified Multi-modal Condition (UMC) framework that employs an embedding refiner and a Fusion Transformer to align text and image prompt embeddings by reducing the modality gap, followed by a redesigned attention mechanism in the generation model that emphasizes correlations between the prompts and the noise image to enable selection of pivotal tokens for consistent outfit generation. The authors claim that experiments on real-world applications and benchmarks show improved visual consistency over state-of-the-art methods.

Significance. If the central claims are supported by quantitative evidence, the work would supply a valuable new benchmark dataset for fashion generation and a concrete architectural approach to multi-modal prompt alignment that could generalize to other conditional generation tasks. The emphasis on unified embeddings and attention redesign directly targets a known challenge in text-image conditioning.

major comments (2)
  1. Abstract: The claim of achieving 'promising result than that of SoTA methods' in visual consistency is unsupported by any quantitative metrics, error bars, ablation studies, or dataset statistics, leaving the central empirical claim without verifiable evidence.
  2. Fusion Transformer description: No ablation isolating the transformer's effect, no pre/post-alignment similarity metrics, and no failure-case analysis are supplied to demonstrate that the redesigned attention reliably closes the text-image embedding gap while preserving garment-specific details needed for consistent generation.
minor comments (2)
  1. Abstract: Grammatical issue in 'achieving promising result than that of SoTA methods'; revise to 'achieving more promising results than SoTA methods'.
  2. Abstract: The phrase 'brand-new' is informal for a journal submission; consider 'new' or 'novel'.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on the empirical claims and the need for additional analysis of the Fusion Transformer. We address each major comment below and will incorporate revisions to strengthen the manuscript.

read point-by-point responses

  1. Referee: Abstract: The claim of achieving 'promising result than that of SoTA methods' in visual consistency is unsupported by any quantitative metrics, error bars, ablation studies, or dataset statistics, leaving the central empirical claim without verifiable evidence.

    Authors: We agree the abstract should be self-contained with quantitative support. The full manuscript reports results in Section 4 using FID, LPIPS, and user-study scores demonstrating improvements over SoTA baselines, along with dataset statistics in Section 3. In revision we will update the abstract to cite specific metrics (e.g., “reducing FID by 0.12 with 95% confidence intervals from five runs”) while retaining the high-level claim. revision: yes

  2. Referee: Fusion Transformer description: No ablation isolating the transformer's effect, no pre/post-alignment similarity metrics, and no failure-case analysis are supplied to demonstrate that the redesigned attention reliably closes the text-image embedding gap while preserving garment-specific details needed for consistent generation.

    Authors: We acknowledge the value of isolating the component’s contribution. We will add an ablation table removing the Fusion Transformer, report cosine-similarity scores between text and image embeddings before and after alignment, and include a qualitative failure-case subsection with examples showing both successful detail preservation and remaining limitations of the attention redesign. revision: yes

Circularity Check

0 steps flagged

No significant circularity in dataset proposal or UMC framework design

full rationale

The paper introduces a new e-commerce dataset (Fashion130K) and a UMC framework consisting of an embedding refiner plus Fusion Transformer for multi-modal alignment. No mathematical derivations, equations, or predictions appear that reduce to fitted parameters, self-definitions, or self-citation chains. Claims of improved visual consistency rest on empirical experiments and comparisons to SoTA methods rather than any internal reduction to the inputs by construction. The work is therefore self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on the effectiveness of the proposed embedding refiner and Fusion Transformer for modality alignment, but the abstract provides no explicit free parameters, axioms, or invented entities.

pith-pipeline@v0.9.0 · 5539 in / 1122 out tokens · 35918 ms · 2026-05-14T21:52:57.867053+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

59 extracted references · 59 canonical work pages · 12 internal anchors

  1. [1]

    Imagen 3.arXiv preprint arXiv:2408.07009, 2024

    Jason Baldridge, Jakob Bauer, Mukul Bhutani, Nicole Brichtova, Andrew Bunner, Lluis Castrejon, Kelvin Chan, Yichang Chen, Sander Dieleman, Yuqing Du, et al. Imagen 3.arXiv preprint arXiv:2408.07009, 2024. 2

    work page arXiv 2024

  2. [2]

    Stephen Batifol, Andreas Blattmann, Frederic Boesel, Sak- sham Consul, Cyril Diagne, Tim Dockhorn, Jack English, Zion English, Patrick Esser, Sumith Kulal, et al. Flux. 1 kontext: Flow matching for in-context image generation and editing in latent space.arXiv e-prints, pages arXiv–2506,

    work page

  3. [3]

    Large Scale GAN Training for High Fidelity Natural Image Synthesis

    Andrew Brock, Jeff Donahue, and Karen Simonyan. Large scale gan training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096, 2018. 2

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  4. [4]

    PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

    Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, et al. Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis.arXiv preprint arXiv:2310.00426, 2023. 2

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  5. [5]

    Magic clothing: Controllable garment-driven image synthesis

    Weifeng Chen, Tao Gu, Yuhao Xu, and Arlene Chen. Magic clothing: Controllable garment-driven image synthesis. In Proceedings of the 32nd ACM International Conference on Multimedia, pages 6939–6948, 2024. 6, 8

    work page 2024

  6. [6]

    Viton-hd: High-resolution virtual try-on via misalignment-aware normalization

    Seunghwan Choi, Sunghyun Park, Minsoo Lee, and Jaegul Choo. Viton-hd: High-resolution virtual try-on via misalignment-aware normalization. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 14131–14140, 2021. 1, 2, 3

    work page 2021

  7. [7]

    Improving diffusion models for vir- tual try-on.arXiv e-prints, pages arXiv–2403, 2024

    Yisol Choi, Sangkyung Kwak, Kyungmin Lee, Hyungwon Choi, and Jinwoo Shin. Improving diffusion models for vir- tual try-on.arXiv e-prints, pages arXiv–2403, 2024. 1, 2

    work page 2024

  8. [8]

    Towards multi-pose guided virtual try-on network

    Haoye Dong, Xiaodan Liang, Xiaohui Shen, Bochao Wang, Hanjiang Lai, Jia Zhu, Zhiting Hu, and Jian Yin. Towards multi-pose guided virtual try-on network. InProceedings of the IEEE/CVF international conference on computer vision, pages 9026–9035, 2019. 3

    work page 2019

  9. [9]

    Scaling Rectified Flow Transformers for High-Resolution Image Synthesis

    Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M ¨uller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et al. Scaling rectified flow transformers for high-resolution image synthesis.arXiv preprint arXiv:2403.03206, 2024. 2, 4

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  10. [10]

    Generative adversarial nets.Advances in neural information processing systems, 27, 2014

    Ian J Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets.Advances in neural information processing systems, 27, 2014. 2

    work page 2014

  11. [11]

    Any2anytryon: Leveraging adaptive position embeddings for versatile virtual clothing tasks

    Hailong Guo, Bohan Zeng, Yiren Song, Wentao Zhang, Ji- aming Liu, and Chuang Zhang. Any2anytryon: Leveraging adaptive position embeddings for versatile virtual clothing tasks. InProceedings of the IEEE/CVF International Con- ference on Computer Vision, pages 19085–19096, 2025. 6, 8

    work page 2025

  12. [12]

    Pulid: Pure and lightning id customization via contrastive alignment.Advances in neural information pro- cessing systems, 37:36777–36804, 2024

    Zinan Guo, Yanze Wu, Chen Zhuowei, Peng Zhang, Qian He, et al. Pulid: Pure and lightning id customization via contrastive alignment.Advances in neural information pro- cessing systems, 37:36777–36804, 2024. 2

    work page 2024

  13. [13]

    Viton: An image-based virtual try-on network

    Xintong Han, Zuxuan Wu, Zhe Wu, Ruichi Yu, and Larry S Davis. Viton: An image-based virtual try-on network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7543–7552, 2018. 3

    work page 2018

  14. [14]

    Emma: Your text-to-image diffusion model can secretly accept multi-modal prompts

    Yucheng Han, Rui Wang, Chi Zhang, Juntao Hu, Pei Cheng, Bin Fu, and Hanwang Zhang. Emma: Your text-to-image diffusion model can secretly accept multi-modal prompts. arXiv preprint arXiv:2406.09162, 2024. 1

    work page arXiv 2024

  15. [15]

    Denoising dif- fusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

    Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising dif- fusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020. 1

    work page 2020

  16. [16]

    An introduction to flow matching and diffusion models.arXiv preprint arXiv:2506.02070, 2025

    Peter Holderrieth and Ezra Erives. An introduction to flow matching and diffusion models.arXiv preprint arXiv:2506.02070, 2025. 4

    work page arXiv 2025

  17. [17]

    Fashionon: Semantic-guided image-based virtual try-on with detailed human and clothing information

    Chia-Wei Hsieh, Chieh-Yun Chen, Chien-Lung Chou, Hong- Han Shuai, Jiaying Liu, and Wen-Huang Cheng. Fashionon: Semantic-guided image-based virtual try-on with detailed human and clothing information. InProceedings of the 27th ACM international conference on multimedia, pages 275– 283, 2019. 3

    work page 2019

  18. [18]

    Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022

    Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022. 6

    work page 2022

  19. [19]

    Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis.arXiv preprint, 2024

    Team K. Kolors: Effective training of diffusion model for photorealistic text-to-image synthesis.arXiv preprint, 2024. 2

    work page 2024

  20. [20]

    A style-based generator architecture for generative adversarial networks

    Tero Karras, Samuli Laine, and Timo Aila. A style-based generator architecture for generative adversarial networks. InProceedings of the IEEE/CVF conference on computer vi- sion and pattern recognition, pages 4401–4410, 2019. 2

    work page 2019

  21. [21]

    Are these the same apple? comparing images based on object intrinsics.Advances in Neural Information Processing Systems, 36:40853–40871, 2023

    Klemen Kotar, Stephen Tian, Hong-Xing Yu, Dan Yamins, and Jiajun Wu. Are these the same apple? comparing images based on object intrinsics.Advances in Neural Information Processing Systems, 36:40853–40871, 2023. 6

    work page 2023

  22. [22]

    Tryongan: Body-aware try-on via layered interpolation.ACM Transactions on Graphics (TOG), 40(4):1–10, 2021

    Kathleen M Lewis, Srivatsan Varadharajan, and Ira Kemelmacher-Shlizerman. Tryongan: Body-aware try-on via layered interpolation.ACM Transactions on Graphics (TOG), 40(4):1–10, 2021. 3

    work page 2021

  23. [23]

    Toward accurate and realistic outfits visualization with atten- tion to details

    Kedan Li, Min Jin Chong, Jeffrey Zhang, and Jingen Liu. Toward accurate and realistic outfits visualization with atten- tion to details. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 15546– 15555, 2021. 3

    work page 2021

  24. [24]

    Anyfit: Controllable virtual try- on for any combination of attire across any scenario.arXiv preprint arXiv:2405.18172, 2024

    Yuhan Li, Hao Zhou, Wenxiang Shang, Ran Lin, Xuanhong Chen, and Bingbing Ni. Anyfit: Controllable virtual try- on for any combination of attire across any scenario.arXiv preprint arXiv:2405.18172, 2024. 2

    work page arXiv 2024

  25. [25]

    net/forum?id=POWv6hDd9XH

    Zhimin Li, Jianwei Zhang, Qin Lin, Jiangfeng Xiong, Yanxin Long, Xinchi Deng, Yingfang Zhang, Xingchao Liu, Minbin Huang, Zedong Xiao, et al. Hunyuan-dit: A powerful multi-resolution diffusion transformer with fine-grained chi- nese understanding.arXiv preprint arXiv:2405.08748, 2024. 2

    work page arXiv 2024

  26. [26]

    Dual diffusion for unified image generation and understanding

    Zijie Li, Henry Li, Yichun Shi, Amir Barati Farimani, Yu- val Kluger, Linjie Yang, and Peng Wang. Dual diffusion for unified image generation and understanding. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 2779–2790, 2025. 4

    work page 2025

  27. [27]

    Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Sys- tems, 35:17612–17625, 2022

    Victor Weixin Liang, Yuhui Zhang, Yongchan Kwon, Ser- ena Yeung, and James Y Zou. Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning.Advances in Neural Information Processing Sys- tems, 35:17612–17625, 2022. 4

    work page 2022

  28. [28]

    Flow Matching for Generative Modeling

    Yaron Lipman, Ricky TQ Chen, Heli Ben-Hamu, Maximil- ian Nickel, and Matt Le. Flow matching for generative mod- eling.arXiv preprint arXiv:2210.02747, 2022. 4

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  29. [29]

    Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

    Xingchao Liu, Chengyue Gong, and Qiang Liu. Flow straight and fast: Learning to generate and transfer data with rectified flow.arXiv preprint arXiv:2209.03003, 2022. 4

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  30. [30]

    Deepfashion: Powering robust clothes recognition and retrieval with rich annotations

    Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, and Xiaoou Tang. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. InProceedings of the IEEE conference on computer vision and pattern recogni- tion, pages 1096–1104, 2016. 3

    work page 2016

  31. [31]

    Ace++: Instruction- based image creation and editing via context-aware content filling.arXiv preprint arXiv:2501.02487, 2025

    Chaojie Mao, Jingfeng Zhang, Yulin Pan, Zeyinzi Jiang, Zhen Han, Yu Liu, and Jingren Zhou. Ace++: Instruction- based image creation and editing via context-aware content filling.arXiv preprint arXiv:2501.02487, 2025. 6, 8

    work page arXiv 2025

  32. [32]

    Dress code: High- resolution multi-category virtual try-on

    Davide Morelli, Matteo Fincato, Marcella Cornia, Federico Landi, Fabio Cesari, and Rita Cucchiara. Dress code: High- resolution multi-category virtual try-on. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2231–2235, 2022. 1, 3

    work page 2022

  33. [33]

    Dreamo: A unified framework for image customization.arXiv preprint arXiv:2504.16915,

    Chong Mou, Yanze Wu, Wenxu Wu, Zinan Guo, Pengze Zhang, Yufeng Cheng, Yiming Luo, Fei Ding, Shiwen Zhang, Xinghui Li, et al. Dreamo: A unified framework for image customization.arXiv preprint arXiv:2504.16915,

    work page arXiv

  34. [34]

    Image based virtual try-on network from unpaired data

    Assaf Neuberger, Eran Borenstein, Bar Hilleli, Eduard Oks, and Sharon Alpert. Image based virtual try-on network from unpaired data. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 5184– 5193, 2020. 3

    work page 2020

  35. [35]

    DINOv2: Learning Robust Visual Features without Supervision

    Maxime Oquab, Timoth ´ee Darcet, Th ´eo Moutakanni, Huy V o, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, et al. Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023. 6

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  36. [36]

    Scalable diffusion models with transformers

    William Peebles and Saining Xie. Scalable diffusion models with transformers. InProceedings of the IEEE/CVF inter- national conference on computer vision, pages 4195–4205,

    work page

  37. [37]

    SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

    Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M ¨uller, Joe Penna, and Robin Rombach. Sdxl: Improving latent diffusion mod- els for high-resolution image synthesis.arXiv preprint arXiv:2307.01952, 2023. 2

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  38. [38]

    Lumina- image 2.0: A unified and efficient image generative frame- work.arXiv preprint arXiv:2503.21758, 2025

    Qi Qin, Le Zhuo, Yi Xin, Ruoyi Du, Zhen Li, Bin Fu, Yiting Lu, Jiakang Yuan, Xinyue Li, Dongyang Liu, et al. Lumina- image 2.0: A unified and efficient image generative frame- work.arXiv preprint arXiv:2503.21758, 2025. 2

    work page arXiv 2025

  39. [39]

    Accept the modality gap: An exploration in the hyperbolic space

    Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, and Ajanthan Thalaiyasingam. Accept the modality gap: An exploration in the hyperbolic space. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 27263–27272, 2024. 4

    work page 2024

  40. [40]

    Hierarchical Text-Conditional Image Generation with CLIP Latents

    Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. Hierarchical text-conditional image gener- ation with clip latents.arXiv preprint arXiv:2204.06125, 1 (2):3, 2022. 2

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  41. [41]

    High-resolution image synthesis with latent diffusion models

    Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj ¨orn Ommer. High-resolution image synthesis with latent diffusion models. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695, 2022. 1, 2

    work page 2022

  42. [42]

    Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation

    Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 22500– 22510, 2023. 2

    work page 2023

  43. [43]

    Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022

    Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. Photorealistic text-to-image diffusion models with deep language understanding.Advances in neural information processing systems, 35:36479–36494, 2022. 2

    work page 2022

  44. [44]

    Denoising Diffusion Implicit Models

    Jiaming Song, Chenlin Meng, and Stefano Ermon. Denoising diffusion implicit models.arXiv preprint arXiv:2010.02502, 2020. 1

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  45. [45]

    Ominicontrol: Minimal and uni- versal control for diffusion transformer.arXiv preprint arXiv:2411.15098, 2024

    Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu Xue, and Xinchao Wang. Ominicontrol: Minimal and uni- versal control for diffusion transformer.arXiv preprint arXiv:2411.15098, 2024. 6, 8

    work page arXiv 2024

  46. [46]

    Mv-vton: Multi-view virtual try-on with diffusion models

    Haoyu Wang, Zhilu Zhang, Donglin Di, Shiliang Zhang, and Wangmeng Zuo. Mv-vton: Multi-view virtual try-on with diffusion models. InProceedings of the AAAI Conference on Artificial Intelligence, pages 7682–7690, 2025. 3

    work page 2025

  47. [47]

    Stablegar- ment: Garment-centric generation via stable diffusion.arXiv preprint arXiv:2403.10783, 2024

    Rui Wang, Hailong Guo, Jiaming Liu, Huaxia Li, Haibo Zhao, Xu Tang, Yao Hu, Hao Tang, and Peipei Li. Stablegar- ment: Garment-centric generation via stable diffusion.arXiv preprint arXiv:2403.10783, 2024. 1, 2

    work page arXiv 2024

  48. [48]

    Qwen-Image Technical Report

    Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, et al. Qwen-image technical report.arXiv preprint arXiv:2508.02324, 2025. 2, 6, 7, 8

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  49. [49]

    OmniGen2: Towards Instruction-Aligned Multimodal Generation

    Chenyuan Wu, Pengfei Zheng, Ruiran Yan, Shitao Xiao, Xin Luo, Yueze Wang, Wanli Li, Xiyan Jiang, Yexin Liu, Junjie Zhou, et al. Omnigen2: Exploration to advanced multimodal generation.arXiv preprint arXiv:2506.18871, 2025. 2, 6, 8

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  50. [50]

    Uso: Unified style and subject-driven generation via disentangled and reward learning.arXiv preprint arXiv:2508.18966, 2025

    Shaojin Wu, Mengqi Huang, Yufeng Cheng, Wenxu Wu, Ji- ahe Tian, Yiming Luo, Fei Ding, and Qian He. Uso: Unified style and subject-driven generation via disentangled and re- ward learning.arXiv preprint arXiv:2508.18966, 2025. 6, 8

    work page arXiv 2025

  51. [51]

    Less-to-more generalization: Unlocking more controllability by in-context generation.arXiv preprint arXiv:2504.02160, 2025

    Shaojin Wu, Mengqi Huang, Wenxu Wu, Yufeng Cheng, Fei Ding, and Qian He. Less-to-more generalization: Unlocking more controllability by in-context generation.arXiv preprint arXiv:2504.02160, 2025. 6, 8

    work page arXiv 2025

  52. [52]

    Omnigen: Unified image genera- tion

    Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xin- grun Xing, Ruiran Yan, Chaofan Li, Shuting Wang, Tiejun Huang, and Zheng Liu. Omnigen: Unified image genera- tion. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 13294–13304, 2025. 6, 8

    work page 2025

  53. [53]

    Ootd- iffusion: Outfitting fusion based latent diffusion for control- lable virtual try-on

    Yuhao Xu, Tao Gu, Weifeng Chen, and Arlene Chen. Ootd- iffusion: Outfitting fusion based latent diffusion for control- lable virtual try-on. InProceedings of the AAAI Conference on Artificial Intelligence, pages 8996–9004, 2025. 1

    work page 2025

  54. [54]

    IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

    Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. Ip- adapter: Text compatible image prompt adapter for text-to- image diffusion models.arXiv preprint arXiv:2308.06721,

    work page internal anchor Pith review Pith/arXiv arXiv

  55. [55]

    Generating high-resolution fashion model images wearing custom outfits

    Gokhan Yildirim, Nikolay Jetchev, Roland V ollgraf, and Urs Bergmann. Generating high-resolution fashion model images wearing custom outfits. InProceedings of the IEEE/CVF international conference on computer vision workshops, pages 0–0, 2019. 3

    work page 2019

  56. [56]

    Pixel-level domain transfer

    Donggeun Yoo, Namil Kim, Sunggyun Park, Anthony S Paek, and In So Kweon. Pixel-level domain transfer. In European conference on computer vision, pages 517–532. Springer, 2016. 3

    work page 2016

  57. [57]

    The unreasonable effectiveness of deep features as a perceptual metric

    Richard Zhang, Phillip Isola, Alexei A Efros, Eli Shecht- man, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. InProceedings of the IEEE conference on computer vision and pattern recogni- tion, pages 586–595, 2018. 6

    work page 2018

  58. [58]

    Virtually trying on new clothing with arbitrary poses

    Na Zheng, Xuemeng Song, Zhaozheng Chen, Linmei Hu, Da Cao, and Liqiang Nie. Virtually trying on new clothing with arbitrary poses. InProceedings of the 27th ACM inter- national conference on multimedia, pages 266–274, 2019. 3

    work page 2019

  59. [59]

    Learning flow fields in attention for controllable person image generation

    Zijian Zhou, Shikun Liu, Xiao Han, Haozhe Liu, Kam Woh Ng, Tian Xie, Yuren Cong, Hang Li, Mengmeng Xu, Juan- Manuel P´erez-R´ua, et al. Learning flow fields in attention for controllable person image generation. InProceedings of the Computer Vision and Pattern Recognition Conference, pages 2491–2501, 2025. 2

    work page 2025