Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
This addresses the high computational cost of video generation models for researchers and practitioners, though it is incremental in optimizing design choices.
The paper tackled the problem of training a video generation foundation model cost-effectively, achieving competitive performance with a 7-billion-parameter model using 665,000 H100 GPU hours, comparable to larger models.
This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parameters (7B) called Seaweed-7B trained from scratch using 665,000 H100 GPU hours. Despite being trained with moderate computational resources, Seaweed-7B demonstrates highly competitive performance compared to contemporary video generation models of much larger size. Design choices are especially crucial in a resource-constrained setting. This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model. Empirically, we make two observations: (1) Seaweed-7B achieves performance comparable to, or even surpasses, larger models trained on substantially greater GPU resources, and (2) our model, which exhibits strong generalization ability, can be effectively adapted across a wide range of downstream applications either by lightweight fine-tuning or continue training. See the project page at https://seaweed.video/