ControlNeXt: Powerful and Efficient Control for Image and Video Generation
MP3•Jakson koti
Manage episode 435200976 series 2954468
Sisällön tarjoaa Rob. Rob tai sen podcast-alustan kumppani lataa ja toimittaa kaiken podcast-sisällön, mukaan lukien jaksot, grafiikat ja podcast-kuvaukset. Jos uskot jonkun käyttävän tekijänoikeudella suojattua teostasi ilman lupaasi, voit seurata tässä https://fi.player.fm/legal kuvattua prosessia.
Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require substantial additional computational resources, especially for video generation, and face challenges in training or exhibit weak control. In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation. We first design a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model. Such a concise structure also allows our method to seamlessly integrate with other LoRA weights, enabling style alteration without the need for additional training. As for training, we reduce up to 90% of learnable parameters compared to the alternatives. Furthermore, we propose another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence. We have conducted various experiments with different base models across images and videos, demonstrating the robustness of our method.
2024: Bohao Peng, Jian Wang, Yuechen Zhang, Wenbo Li, Mingchang Yang, Jiaya Jia
https://arxiv.org/pdf/2408.06070
…
continue reading
2024: Bohao Peng, Jian Wang, Yuechen Zhang, Wenbo Li, Mingchang Yang, Jiaya Jia
https://arxiv.org/pdf/2408.06070
298 jaksoa