Skip to content
Clothsy AI Talk to us
Clothsy AI Talk to us

AppendixReference6 min readVersion 1.2 · 30 September 2026

References

Papers, model cards, licences and official pages, numbered exactly as in the proposal.

Every source the programme draws on: papers, model cards, licences and official pages. Numbers match the citations throughout these docs and in the proposal PDF. Key public figures were re-checked against their primary sources on 30 September 2026.

  1. [1]Coresight Research. The True Cost of Apparel Returns: Alarming Return Rates Require Loss-Minimization Solutions. 2023. coresight.com/research/the-true-cost-of-apparel-returns-alarming-return-rates-require-loss-minimization-solutions
  2. [2]Google. Virtual apparel try-on in the UK and India. Google Shopping blog, December 2025. blog.google/products-and-platforms/products/shopping/virtual-apparel-try-on-uk-india
  3. [3]Alibaba Taobao. Tstars-Tryon 1.0. arXiv:2604.19748, April 2026. arxiv.org/abs/2604.19748
  4. [4]Choi et al. VITON-HD: High-Resolution Virtual Try-On. CVPR 2021. Dataset licence CC BY-NC 4.0. github.com/shadow2496/VITON-HD
  5. [5]Morelli et al. Dress Code: High-Resolution Multi-Category Virtual Try-On. ECCV 2022. Dataset access terms. github.com/aimagelab/dress-code
  6. [6]Virtual Try-On for Cultural Clothing: A Benchmarking Study (BD-VITON). arXiv:2603.07291, March 2026. Paper licensed CC BY-NC-SA 4.0; no separate dataset licence stated. arxiv.org/abs/2603.07291
  7. [7]FabricVTON. Internal technical documentation: What Is Built (updated 18 and 25 September 2026) and Project Status (24 September 2026). Available to reviewers on request.
  8. [8]National Retail Federation and Happy Returns. Consumers Expected to Return Nearly $850 Billion in Merchandise in 2025. Press release, 2025. nrf.com/media-center/press-releases/consumers-expected-to-return-nearly-850-billion-in-merchandise-in-2025
  9. [9]Grand View Research. Virtual Fitting Room Market Size, Share and Trends Analysis Report, 2025 to 2030. www.grandviewresearch.com/industry-analysis/virtual-fitting-room-market
  10. [10]Store Leads. Shopify Stores in the Apparel Category. Report as updated on 25 September 2026. storeleads.app/reports/shopify/category/Apparel
  11. [11]Store Leads. WooCommerce Stores in the Apparel Category. Report as updated on 25 September 2026. storeleads.app/reports/woocommerce/category/Apparel
  12. [12]TechCrunch. Google's new AI feature lets you virtually try on clothes. 24 July 2025. techcrunch.com/2025/07/24/googles-new-ai-feature-lets-you-virtually-try-on-clothes
  13. [13]Inditex. FY2025 Results. 2026. www.inditex.com/itxcomweb/us/en/press/news-detail/b870d5ec-6b7e-491d-b38e-340cd69036df/fy2025-results
  14. [14]Google Cloud. Virtual Try-On on Vertex AI (virtual-try-on-001). Documentation. docs.cloud.google.com/vertex-ai/generative-ai/docs/models/imagen/virtual-try-on-preview-08-04
  15. [15]JD.com. Oxygen-TryOn. arXiv:2607.21694, July 2026. arxiv.org/abs/2607.21694
  16. [16]Feng, Chen, Shan and Kemelmacher-Shlizerman. Layering Virtual Try-On. ECCV 2026. arXiv:2607.22924. arxiv.org/abs/2607.22924
  17. [17]Zhou et al. Learning Flow Fields in Attention for Controllable Person Image Generation (Leffa). CVPR 2025. arXiv:2412.08486. arxiv.org/abs/2412.08486
  18. [18]Chong et al. CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models. ICLR 2025. arXiv:2407.15886. arxiv.org/abs/2407.15886
  19. [19]Rajput and Aneja. IndoFashion: Apparel Classification for Indian Ethnic Clothes. CVPR Workshops 2021. arXiv:2104.02830. arxiv.org/abs/2104.02830
  20. [20]DIVA: Indian virtual try-on (IndicViton). ECCV 2024 Workshops, Springer. link.springer.com/chapter/10.1007/978-3-031-91569-7_23
  21. [21]Awesome Try-On Models (curated list of try-on research), updated 3 September 2026. github.com/Zheng-Chong/Awesome-Try-On-Models
  22. [22]SiCo: size-controllable virtual try-on. DIS 2025. arXiv:2408.02803. arxiv.org/abs/2408.02803
  23. [23]Google. Generative virtual try-on for apparel in Google Shopping. June 2023. blog.google/products/shopping/ai-virtual-try-on-google-shopping
  24. [24]Monk, E. and Google. The Monk Skin Tone Scale. skintone.google
  25. [25]Xu et al. OOTDiffusion: Outfitting Fusion Based Latent Diffusion for Controllable Virtual Try-On. AAAI 2025. arXiv:2403.01779. arxiv.org/abs/2403.01779
  26. [26]Choi et al. Improving Diffusion Models for Authentic Virtual Try-On in the Wild (IDM-VTON). ECCV 2024. arXiv:2403.05139. arxiv.org/abs/2403.05139
  27. [27]Jiang et al. FitDiT: Advancing the Authentic Garment Details for High-Fidelity Virtual Try-On. arXiv:2411.10499. arxiv.org/abs/2411.10499
  28. [28]Qwen Team. Qwen-Image-2.1 licence (Qwen Research License Agreement), September 2026. github.com/QwenLM/Qwen-Image-2.1/blob/main/LICENSE
  29. [29]Black Forest Labs. FLUX.2 [klein] 9B licence (FLUX Non-Commercial License). huggingface.co/black-forest-labs/FLUX.2-klein-9B/blob/main/LICENSE.md
  30. [30]FASHN AI. FASHN VTON v1.5: Efficient Maskless Virtual Try-On in Pixel Space. Research page. fashn.ai/research/vton-1-5
  31. [31]Zhu et al. TryOnDiffusion: A Tale of Two UNets. CVPR 2023. arXiv:2306.08276. arxiv.org/abs/2306.08276
  32. [32]Morelli et al. LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On. ACM MM 2023. arXiv:2305.13501. arxiv.org/abs/2305.13501
  33. [33]Kim et al. StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On. CVPR 2024. arXiv:2312.01725. arxiv.org/abs/2312.01725
  34. [34]OmniTry: mask-free virtual try-on for wearable objects. arXiv:2508.13632. arxiv.org/abs/2508.13632
  35. [35]Voost: a diffusion transformer for joint virtual try-on and try-off. SIGGRAPH Asia 2025. arXiv:2508.04825. arxiv.org/abs/2508.04825
  36. [36]TAMF-VTON. arXiv:2607.14807, July 2026. arxiv.org/abs/2607.14807
  37. [37]RealFit. arXiv:2609.25881, September 2026. arxiv.org/abs/2609.25881
  38. [38]FastFit: cacheable multi-reference virtual try-on. arXiv:2508.20586. arxiv.org/abs/2508.20586
  39. [39]CORAL: correspondence-aligned virtual try-on. arXiv:2602.17636, 2026. arxiv.org/abs/2602.17636
  40. [40]FASHN AI. fashn-vton-1.5 model card, Hugging Face. huggingface.co/fashn-ai/fashn-vton-1.5
  41. [41]VTEdit-Bench. ECCV 2026. arXiv:2603.11734. arxiv.org/abs/2603.11734
  42. [42]TryOnReward. arXiv:2609.13259, September 2026. arxiv.org/abs/2609.13259
  43. [43]DirectTryOn. arXiv:2605.12939, May 2026. arxiv.org/abs/2605.12939
  44. [44]FASHN AI. Open-sourcing FASHN VTON v1.5. Blog post, 2026. fashn.ai/blog/fashn-vton-1-5-open-source-release
  45. [45]FASHN AI. API pricing. Help centre. help.fashn.ai/plans-and-pricing/api-pricing
  46. [46]ByteDance Seed. Seedream 4.0 officially released. September 2025. seed.bytedance.com/en/blog/seedream-4-0-officially-released-beyond-drawing-into-imagination
  47. [47]Google Cloud. Virtual try-on technology with Google Cloud AI (Meesho case). July 2024. cloud.google.com/blog/products/ai-machine-learning/virtual-try-on-technology-with-google-cloud-ai
  48. [48]Qwen Team. Qwen-Image-Edit-2511 model card (Apache-2.0). huggingface.co/Qwen/Qwen-Image-Edit-2511
  49. [49]Black Forest Labs. FLUX.2 [klein] base 4B model card (Apache-2.0). huggingface.co/black-forest-labs/FLUX.2-klein-base-4B
  50. [50]Meituan LongCat. LongCat-Image-Edit model card. huggingface.co/meituan-longcat/LongCat-Image-Edit
  51. [51]HiDream. HiDream-O1-Image model card (MIT). huggingface.co/HiDream-ai/HiDream-O1-Image
  52. [52]Garments2Look. CVPR 2026. arXiv:2603.14153. arxiv.org/abs/2603.14153
  53. [53]OpenVTON-Bench. arXiv:2601.22725, January 2026. arxiv.org/abs/2601.22725
  54. [54]VTBench: a hierarchical virtual try-on benchmark. arXiv:2505.19571, May 2025. arxiv.org/abs/2505.19571
  55. [55]VTONQA. arXiv:2601.02945, January 2026. arxiv.org/abs/2601.02945
  56. [56]VTON-IQA and VTON-QBench. arXiv:2603.13057, March 2026. arxiv.org/abs/2603.13057
  57. [57]Velioglu et al. TryOffDiff: virtual try-off with diffusion models. BMVC 2025. arXiv:2411.18350. arxiv.org/abs/2411.18350
  58. [58]Karras et al. FIT: a fit-aware virtual try-on dataset. SIGGRAPH 2026. arXiv:2604.08526. arxiv.org/abs/2604.08526
  59. [59]FitControler. ECCV 2026. arXiv:2512.24016. arxiv.org/abs/2512.24016
  60. [60]BooW-VTON: mask-free in-the-wild virtual try-on. CVPR 2025. arXiv:2408.06047. arxiv.org/abs/2408.06047
  61. [61]kohya-ss. musubi-tuner documentation for Qwen-Image training. github.com/kohya-ss/musubi-tuner/blob/main/docs/qwen_image.md
  62. [62]LightX2V. Qwen-Image-Edit-2511-Lightning (few-step LoRA). huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning
  63. [63]CVPR 2027. Key dates. cvpr.thecvf.com/Conferences/2027/Dates
  64. [64]NeurIPS 2026. Call for Evaluations and Datasets. neurips.cc/Conferences/2026/CallForEvaluationsDatasets
  65. [65]Anusandhan National Research Foundation. Prime Minister Early Career Research Grant. anrfonline.in/ANRF/ecrg_anrf?HomePage=New
  66. [66]Ministry of Electronics and Information Technology. TIDE 2.0 scheme. msh.meity.gov.in/schemes/tide
  67. [67]IndiaAI Mission. Compute portal eligibility criteria. compute.indiaai.gov.in/eligibilitycriteria
  68. [68]Startup India. Startup Schemes Playbook, June 2026. www.startupindia.gov.in/content/dam/startupindia/homebanners/Startup-Schemes-Playbook-June-2026.pdf
  69. [69]EU Artificial Intelligence Act, Article 50: Transparency obligations. artificialintelligenceact.eu/article/50
  70. [70]Decart. Platform pricing: Lucy VTON realtime at USD 0.02 per second, 2026. docs.platform.decart.ai/getting-started/pricing
  71. [71]LiveVVT: High-Fidelity Video Virtual Try-On in Real Time. arXiv:2608.26714, August 2026. arxiv.org/abs/2608.26714
  72. [72]Decart. Realtime virtual try-on (Lucy VTON 3.5) documentation, 2026. docs.platform.decart.ai/models/realtime/virtual-try-on
  73. [73]Decart. Decart raises USD 300M; over USD 450 million raised to date. May 2026. decart.ai/publications/decart-raises-300m-tech-leaders-back-the-company-as-both-customers-and-investors
  74. [74]Google Labs. Doppl help centre: the app closed on 30 April 2026 and try-on moved into Search. support.google.com/labs/answer/16537062?hl=en
  75. [75]FASHN AI. Image-to-Video API reference. docs.fashn.ai/api-reference/image-to-video
  76. [76]Luma AI. Ray 3.2 video-to-video, May 2026. lumalabs.ai/learning-center/articles/ray-3-2-video-to-video
  77. [77]Runway. Aleph 2.0 video editing. runway.com/product/aleph-2
  78. [78]Fang et al. ViViD: Video Virtual Try-On using Diffusion Models. arXiv:2405.11794, 2024. arxiv.org/abs/2405.11794
  79. [79]Chong et al. CatV2TON: temporal concatenation for image and video try-on. CVPR 2025 Workshops. arXiv:2501.11325. arxiv.org/abs/2501.11325
  80. [80]MagicTryOn: video virtual try-on on Wan2.1. arXiv:2505.21325, 2025. arxiv.org/abs/2505.21325
  81. [81]DreamVVT: keyframe-first video virtual try-on. ByteDance. arXiv:2508.02807, 2025. arxiv.org/abs/2508.02807
  82. [82]KeyTailor: instruction-guided keyframes for video try-on. CVPR 2026. arXiv:2512.20340. arxiv.org/abs/2512.20340
  83. [83]Vanast: animation and garment transfer from one image. CVPR 2026. arXiv:2604.04934. arxiv.org/abs/2604.04934
  84. [84]BooM-VVT: mask-free video try-on with garment-sensitive keyframes. ACM MM 2026. arXiv:2609.04120. arxiv.org/abs/2609.04120
  85. [85]UniVVT: video try-on without masks, pose or warping. arXiv:2608.05745, August 2026. arxiv.org/abs/2608.05745
  86. [86]Vidu S2-Editing: real-time video editing adapted to causal streaming. arXiv:2609.11638, September 2026. arxiv.org/abs/2609.11638
  87. [87]Yin et al. From Slow Bidirectional to Fast Autoregressive Video Diffusion Models (CausVid). arXiv:2412.07772. arxiv.org/abs/2412.07772
  88. [88]Decart. MirageLSD: live stream diffusion technical report, July 2025 (archived copy). web.archive.org/web/20250918033439/https://about.decart.ai/publications/mirage
  89. [89]Huang et al. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion. arXiv:2506.08009. arxiv.org/abs/2506.08009
  90. [90]Decart. Lucy 2.5: raising the bar for live AI, July 2026. decart.ai/publications/lucy-2-5-raising-the-bar-for-live-ai
  91. [91]ByteDance Seed. Seaweed APT2: autoregressive adversarial post-training for real-time video. seaweed-apt.com/2
  92. [92]NVIDIA. LongLive: Real-time Interactive Long Video Generation. arXiv:2509.22622. arxiv.org/abs/2509.22622
  93. [93]Krea. Krea Realtime 14B. www.krea.ai/blog/krea-realtime-14b
  94. [94]StreamDiffusionV2. MLSys 2026. arXiv:2511.07399. arxiv.org/abs/2511.07399
  95. [95]JD. JoyAI-Video-Edit: real-time instruction video editing (Apache-2.0). arXiv:2608.03974. arxiv.org/abs/2608.03974
  96. [96]Pika. PikaStream 1.0: real-time video chat, April 2026. pika.art/blog/introducing-real-time-video-chat
  97. [97]Wan Team. Wan2.1 open video foundation models (Apache-2.0). github.com/Wan-Video/Wan2.1
  98. [98]Decart. Network requirements for realtime sessions. docs.platform.decart.ai/integrations/network-requirements
  99. [99]Lightricks. LTX-2.x Community License. github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x
  100. [100]Tencent. HunyuanVideo 1.5 licence (Tencent Hunyuan Community License). github.com/Tencent-Hunyuan/HunyuanVideo-1.5/blob/master/LICENSE
  101. [101]Wan Team. Wan2.2 and Wan2.2-Animate (Apache-2.0). huggingface.co/Wan-AI/Wan2.2-Animate-14B
  102. [102]TripVVT: synthetic triplets for video try-on, and the TripVVT-10K dataset (CC BY-NC 4.0). arXiv:2604.27958. arxiv.org/abs/2604.27958
  103. [103]MV-Fashion: multi-view studio fashion video dataset (CC BY-NC-SA 4.0). CVPR 2026. arXiv:2603.08147. arxiv.org/abs/2603.08147
  104. [104]Shutterstock. Data licensing and the contributor fund. submit.shutterstock.com/help/en/articles/10594694-shutterstock-data-licensing-and-the-contributor-fund
  105. [105]Pexels. Terms of service, including limits on machine-learning use. www.pexels.com/terms-of-service
  106. [106]Teed and Deng. RAFT optical flow (BSD-3-Clause). github.com/princeton-vl/RAFT
  107. [107]Meta. SAM 2: Segment Anything in Images and Videos (Apache-2.0). github.com/facebookresearch/sam2
  108. [108]OpenMMLab. MMPose and RTMPose (Apache-2.0). github.com/open-mmlab/mmpose
  109. [109]LiveKit. Open-source WebRTC media server. github.com/livekit/livekit
  110. [110]VBench: comprehensive benchmark suite for video generative models. github.com/Vchitect/VBench
  111. [111]FabricVTON. Safety guardrails: research and implementation plan, 29 September 2026. Internal; available to reviewers on request.
  112. [112]NVIDIA. Inception programme for startups. www.nvidia.com/en-us/startups
  113. [113]Microsoft for Startups. learn.microsoft.com/en-us/startups
  114. [114]AWS Activate credits. aws.amazon.com/startups/credits
  115. [115]Google for Startups Cloud Program benefits. cloud.google.com/startup/benefits
  116. [116]Google for Startups Accelerator: India. startup.google.com/programs/accelerator/india
  117. [117]H&M Foundation. Global Change Award 2027, via The Mills Fabrica. themillsfabrica.com/events/global-change-award-2027
  118. [118]LVMH. La Maison des Startups and technology partners. www.lvmh.com/en/startups-tech-partners
  119. [119]Chen et al. Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking. CVPR 2025. arXiv:2504.05838. arxiv.org/abs/2504.05838