Goku: Flow Based Video Generative Foundation Models
Journal:
arXiv
Published Date:
Feb 7, 2025
Abstract
This paper introduces Goku, a state-of-the-art family of joint
image-and-video generation models leveraging rectified flow Transformers to
achieve industry-leading performance. We detail the foundational elements
enabling high-quality visual generation, including the data curation pipeline,
model architecture design, flow formulation, and advanced infrastructure for
efficient and robust large-scale training. The Goku models demonstrate superior
performance in both qualitative and quantitative evaluations, setting new
benchmarks across major tasks. Specifically, Goku achieves 0.76 on GenEval and
83.65 on DPG-Bench for text-to-image generation, and 84.85 on VBench for
text-to-video tasks. We believe that this work provides valuable insights and
practical advancements for the research community in developing joint
image-and-video generation models.
