# Virtual Try-On on Tstars-VTON Single-Garment 1.0 (test) Source: [Virtual Try-On on Tstars-VTON Single-Garment 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-04-23T10:04:47.839Z Evaluation of Virtual Try-On performance on the test split of the Tstars-VTON Single-Garment 1.0 dataset, reporting subjective quality metrics including Overall, Identity Consistency, Garment Fidelity, Background Preservation, and Physical & Structural Logic. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Virtual Try-On | | Dataset (including any stated split) | Tstars-VTON Single-Garment 1.0 (test) | | Metric | Overall Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 12 of 12 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Overall Score](): Higher is better; unit: SCALAR. - [Identity Consistency](): Higher is better; unit: SCALAR. - [Garment Fidelity](): Higher is better; unit: SCALAR. - [Background Preservation](): Higher is better; unit: SCALAR. - [Physical & Structural Logic](): Higher is better; unit: SCALAR. ## Recorded results | Method | Overall Score | Result date | Report paper | | --- | --- | --- | --- | | Tstars-Tryon 1.0 | 9.372 | Not recorded | 69e85c027d0172140ec8136b | | Seedream5 lite | 9.301 | Not recorded | 69e85c027d0172140ec8136b | | Nano Banana Pro | 9.229 | Not recorded | 69e85c027d0172140ec8136b | | GPT-Image-1.5 | 8.892 | Not recorded | 69e85c027d0172140ec8136b | | FireRed-Image-Edit-1.1 | 8.863 | Not recorded | 69e85c027d0172140ec8136b | | FLUX.2-klein-9B | 8.797 | Not recorded | 69e85c027d0172140ec8136b | | FLUX.2-dev | 8.764 | Not recorded | 69e85c027d0172140ec8136b | | QwenEdit-2511 | 8.121 | Not recorded | 69e85c027d0172140ec8136b | | CatVTON | 6.663 | Not recorded | 69e85c027d0172140ec8136b | | FastFit | 6.448 | Not recorded | 69e85c027d0172140ec8136b | | Leffa | 6.048 | Not recorded | 69e85c027d0172140ec8136b | | FitDiT | 5.152 | Not recorded | 69e85c027d0172140ec8136b | ### Tstars-Tryon 1.0 Overall Score: 9.372. Result ID: 69e9eeac47f34ce924d1a299. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Proposed Method"}. This record does not assert independent reproduction. ### Seedream5 lite Overall Score: 9.301. Result ID: 69e9eeac47f34ce924d1a298. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Proprietary / Gen-Edit"}. This record does not assert independent reproduction. ### Nano Banana Pro Overall Score: 9.229. Result ID: 69e9eeac47f34ce924d1a297. [Reporting paper]() Recorded evaluation configuration: {"Method Category":"Proprietary / Gen-Edit"}. This record does not assert independent reproduction. ### GPT-Image-1.5 Overall Score: 8.892. Result ID: 69e9eeac47f34ce924d1a296. [Reporting paper]() Recorded evaluation configuration: {"Method Category":"Proprietary / Gen-Edit","Notes":"Failed for 120 test cases, metrics calculated on remaining"}. This record does not assert independent reproduction. ### FireRed-Image-Edit-1.1 Overall Score: 8.863. Result ID: 69e9eeac47f34ce924d1a295. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Proprietary / Gen-Edit"}. This record does not assert independent reproduction. ### FLUX.2-klein-9B Overall Score: 8.797. Result ID: 69e9eeac47f34ce924d1a294. [Reporting paper]() Recorded evaluation configuration: {"Method Category":"Proprietary / Gen-Edit"}. This record does not assert independent reproduction. ### FLUX.2-dev Overall Score: 8.764. Result ID: 69e9eeac47f34ce924d1a293. [Reporting paper]() Recorded evaluation configuration: {"Method Category":"Proprietary / Gen-Edit"}. This record does not assert independent reproduction. ### QwenEdit-2511 Overall Score: 8.121. Result ID: 69e9eeac47f34ce924d1a292. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Proprietary / Gen-Edit"}. This record does not assert independent reproduction. ### CatVTON Overall Score: 6.663. Result ID: 69e9eeac47f34ce924d1a28e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Academic SOTA"}. This record does not assert independent reproduction. ### FastFit Overall Score: 6.448. Result ID: 69e9eeac47f34ce924d1a291. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Academic SOTA"}. This record does not assert independent reproduction. ### Leffa Overall Score: 6.048. Result ID: 69e9eeac47f34ce924d1a28f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Method Category":"Academic SOTA"}. This record does not assert independent reproduction. ### FitDiT Overall Score: 5.152. Result ID: 69e9eeac47f34ce924d1a290. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Method Category":"Academic SOTA"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.