Views
No views yet
outputs/: pretrained checkpointsbuffers/vaes/: VAE checkpoints and latent statisticsbuffers/refs/: reference files for FID evaluation| Checkpoint | Network | Steps | FID50K |
|---|---|---|---|
2026.02.15KST14.22.08-base4 | FlowMapTiT-B/4 (SD-VAE, TrigFlow) | 400K | 14.58 |
2026.01.18KST19.26.11-xlarge1 | ADiT-XL/1 (VA-VAE, Linear) | 600K | 2.30 |
outputs and buffers directories at the top level of
the code repository, then run the provided training or evaluation scripts.bash eval.sh1@misc{kim2026stabilizingconsistencytrainingflow,
2 title={Stabilizing Consistency Training: A Flow Map Analysis and Self-Distillation},
3 author={Youngjoong Kim and Duhoe Kim and Woosung Kim and Jaesik Park},
4 year={2026},
5 eprint={2601.22679},
6 archivePrefix={arXiv},
7 primaryClass={cs.LG},
8 url={https://arxiv.org/abs/2601.22679},
9}