Live demo of epfl-vita/flux2-klein-1step-rdm —
FLUX.2-klein-4B distilled from 4 denoising steps to one with Representation Distribution Matching (RDM).
| GenEval ↑ | PickScore-COCO ↑ | steps | |
|---|---|---|---|
| this model | 0.826 | 22.76 | 1 |
| FLUX.2-klein-4B teacher | 0.794 | 22.58 | 4 |
Pipeline: prompt → Qwen3-4B ctx → fresh noise → 1-step flow-matching Euler → FLUX.2 VAE decode (identical to the evaluated pipeline). Runs on ZeroGPU; the first generation loads the models (~2 min).
Representation Distribution Matching for One-Step Visual Generation. arXiv:2607.02375 · Hugging Face Papers · Project page · Code
@article{feng2026rdm,
title={Representation Distribution Matching for One-Step Visual Generation},
author={Feng, Lan and Li, Wuyang and Zablocki, {\'E}loi and Cord, Matthieu and Alahi, Alexandre},
journal={arXiv preprint arXiv:2607.02375},
year={2026}
}
9 commits
2 commits
Live demo of epfl-vita/flux2-klein-1step-rdm —
FLUX.2-klein-4B distilled from 4 denoising steps to one with Representation Distribution Matching (RDM).
| GenEval ↑ | PickScore-COCO ↑ | steps | |
|---|---|---|---|
| this model | 0.826 | 22.76 | 1 |
| FLUX.2-klein-4B teacher | 0.794 | 22.58 | 4 |
Pipeline: prompt → Qwen3-4B ctx → fresh noise → 1-step flow-matching Euler → FLUX.2 VAE decode (identical to the evaluated pipeline). Runs on ZeroGPU; the first generation loads the models (~2 min).
Representation Distribution Matching for One-Step Visual Generation. arXiv:2607.02375 · Hugging Face Papers · Project page · Code
@article{feng2026rdm,
title={Representation Distribution Matching for One-Step Visual Generation},
author={Feng, Lan and Li, Wuyang and Zablocki, {\'E}loi and Cord, Matthieu and Alahi, Alexandre},
journal={arXiv preprint arXiv:2607.02375},
year={2026}
}
9 commits
2 commits