Optical-Flow Guided Prompt Optimization for Coherent Video Generation

TL;DR

This paper introduces MotionPrompt, a novel optical-flow guided prompt optimization framework that enhances temporal coherence in video generation by training a discriminator to guide learnable prompt tokens during diffusion sampling.

Contribution

We propose a new method that uses optical flow and a discriminator to optimize prompts, improving temporal consistency in diffusion-based video generation.

Findings

Generated videos exhibit improved temporal coherence.

Method maintains high visual fidelity.

Effective across multiple diffusion models.

Abstract

While text-to-video diffusion models have made significant strides, many still face challenges in generating videos with temporal consistency. Within diffusion frameworks, guidance techniques have proven effective in enhancing output quality during inference; however, applying these methods to video diffusion models introduces additional complexity of handling computations across entire sequences. To address this, we propose a novel framework called MotionPrompt that guides the video generation process via optical flow. Specifically, we train a discriminator to distinguish optical flow between random pairs of frames from real videos and generated ones. Given that prompts can influence the entire video, we optimize learnable token embeddings during reverse sampling steps by using gradients from a trained discriminator applied to random frame pairs. This approach allows our method to generate visually coherent video sequences that closely reflect natural motion dynamics, without compromising the fidelity of the generated content. We demonstrate the effectiveness of our approach across various models.