Continuous Adversarial Flow Models
For practitioners of generative modeling, this method offers a post-training refinement that significantly boosts sample quality of existing flow-matching models.
Continuous adversarial flow models improve guidance-free FID on ImageNet 256px from 8.26 to 3.63 for SiT and from 7.17 to 3.57 for JiT, and also enhance text-to-image generation on GenEval and DPG benchmarks.
We propose continuous adversarial flow models, a type of continuous-time flow model trained with an adversarial objective. Unlike flow matching, which uses a fixed mean-squared-error criterion, our approach introduces a learned discriminator to guide training. This change in objective induces a different generalized distribution, which empirically produces samples that are better aligned with the target data distribution. Our method is primarily proposed for post-training existing flow-matching models, although it can also train models from scratch. On the ImageNet 256px generation task, our post-training substantially improves the guidance-free FID of latent-space SiT from 8.26 to 3.63 and of pixel-space JiT from 7.17 to 3.57. It also improves guided generation, reducing FID from 2.06 to 1.53 for SiT and from 1.86 to 1.80 for JiT. We further evaluate our approach on text-to-image generation, where it achieves improved results on both the GenEval and DPG benchmarks.