magnusdtd/ViStableDiffusion download history

magnusdtd/ViStableDiffusion is a question answering dataset on the Hugging Face Hub. In the last 30 days it was downloaded 33 times (2 in the last 7 days), and 329 times in total. It ranks #254,552 among datasets by monthly downloads.

This dataset was generated using Qwen3-VL 4B to generate captions for the Vietnamese Scene Text Spotting Dataset (Vintext). There are some cases where the model generates hallucinatory captions and repeats words, but I'm too lazy to fix them manually ;)).

Open magnusdtd/ViStableDiffusion on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.