Author

Zhan-Hao Liang

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs

MiniDog, a framework that enables pretraining diffusion transformers in 55 minutes and fine-tuning in another 15 minutes on four 3090 GPUs is developed, which supports FID, HPSv2 score, PickScore, and various VAE reconstruction metrics.

Reyhaneh Esmailizadeh, Xing-Jian Leng, Zhan-Hao Liang et al. · 0 citations