TryOn
Datasets
All datasets matching “TryOn”VITON-HD-TESTtts-pretrain-clones-3m
TTS Pretrain Clones (3M)
2,967,779 clone utterances across 2971 English speakers.
Sample rate: 44.1 kHz, WAV in Parquet
Generated by echo-tts synthesizing English text on speaker latents
derived from Qwen3-TTS VoiceDesign base speakers. Per speaker:
10 voice-clone latents × 100 texts. The first utterance of each
speaker (row 0) is published separately in the companion refs set.
Coverage: speakers 1-60 + 61 (partial, 749 rows) + 91-3000. Thirty
speakers (61's tail + 62-90) are… See the full description on the dataset page: https://huggingface.co/datasets/TryOnVirtual/tts-pretrain-clones-3m.Indian-Style-Vritual-Tryon-DatasetThis dataset is create from the public whatsapp groups which are sharing the images.
Each folder contains a indian clothes design and its original photoshoot of the same clothes with a person wearing it.
This can be used for training dataset for virtual try-on ai models.
virtual-tryon-expanded-productstryon_testtryon_test2