PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
This work addresses efficiency for video generation tasks, but it is incremental as it builds on existing pyramidal models by adapting pretrained ones.
The authors tackled the problem of high computational cost in video diffusion models by converting a pretrained model into a pyramidal one through low-cost finetuning, achieving this without quality degradation and exploring step distillation to enhance inference efficiency.
Recently proposed pyramidal models decompose the conventional forward and backward diffusion processes into multiple stages operating at varying resolutions. These models handle inputs with higher noise levels at lower resolutions, while less noisy inputs are processed at higher resolutions. This hierarchical approach significantly reduces the computational cost of inference in multi-step denoising models. However, existing open-source pyramidal video models have been trained from scratch and tend to underperform compared to state-of-the-art systems in terms of visual plausibility. In this work, we present a pipeline that converts a pretrained diffusion model into a pyramidal one through low-cost finetuning, achieving this transformation without degradation in quality of output videos. Furthermore, we investigate and compare various strategies for step distillation within pyramidal models, aiming to further enhance the inference efficiency. Our results are available at https://qualcomm-ai-research.github.io/PyramidalWan.