NextGAN：面向图像与视频生成的简洁可扩展 GAN 训练方法
NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation
AI 导读
NEXTGAN 提出一种新的对抗训练方法，在冻结表示空间中对 critic 输入梯度进行回归，实现一步或少步图像与视频生成。该方法可适配参数规模最高 14B 的预训练图像和视频生成器，无需辅助损失、在线 teacher 分数或轨迹。
正文 · 原文
Abstract:Adversarial training enables one- and few-step image and video generation, but conventional adversarial losses supervise critic values without directly specifying the gradients used to update the generator. We present NEXTGAN, which trains a scalar critic by regressing its input gradient onto displacements between independently paired reference and generated features at interpolated locations in frozen representation spaces. For a fixed generator, this regression is equivalent to an adversarial objective with a gradient-energy penalty, while the generator retains the standard potential-based GAN update. The same objective adapts pre-trained image and video generators with up to 14B parameters, without auxiliary losses, online teacher scores, or trajectories. On ImageNet $256 \times 256$, NEXTGAN achieves one-step FIDs of 2.87 with pixel-space JiT-B and 1.54 with latent-space DiT-XL/1; its adversarial form further reaches 1.36. For text-to-video generation, a single trained Wan2.1-1.3B model supports one-, two-, and four-step sampling, achieving the highest VBench total scores among the compared 1.3B methods at one and two steps. At two steps, NEXTGAN scores 83.13, exceeding rCM and AnyFlow by 1.25 and 0.47 points, respectively. Code is available at this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06270 [cs.CV] |
| (or arXiv:2611.06270v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06270 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinhao Lou [view email]
[v1]
Wed, 4 Nov 2026 10:16:06 UTC (9,244 KB)
来源：arXiv cs.AI · arxiv.org