Metraipolis › archive › dc_338a0d49700e
NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation — arXiv:2611.06270
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.06270
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:17:49.525Z
- SHA-256 of the archived text
980d6642282f9dfc4890db1f98bc45b062e9ab2fe512140eaa096e379c2d1afb- Stable URL of this page
https://metraipolis.com/documento/dc_338a0d49700e
How to cite
NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation — arXiv:2611.06270 — arXiv (en), https://arxiv.org/abs/2611.06270 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_338a0d49700e (Metraipolis archive dc_338a0d49700e, sha256 980d6642282f9dfc4890db1f98bc45b062e9ab2fe512140eaa096e379c2d1afb)
BibTeX
@misc{dc338a0d49700e,
title = {NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation — arXiv:2611.06270},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.06270},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_338a0d49700e; sha256 980d6642282f9dfc4890db1f98bc45b062e9ab2fe512140eaa096e379c2d1afb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06270. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.06270 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:12:49.051Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).