Recent advances in text-to-video generation have harnessed the power of diffusion models to create visually compelling content conditioned on text prompts. However, they usually encounter high computational costs and often struggle to produce videos with coherent physical motions. To tackle these issues, we propose GPT4Motion, a training-free framework that leverages the planning capability of large language models such as GPT, the physical simulation strength of Blender, and the excellent image generation ability of text-to-image diffusion models to enhance the quality of video synthesis. Specifically, GPT4Motion employs GPT-4 to generate a Blender script based on a user textual prompt, which commands Blender's built-in physics engine to craft fundamental scene components that encapsulate coherent physical motions across frames. Then these components are inputted into Stable Diffusion to generate a video aligned with the textual prompt. Experimental results on three basic physical motion scenarios, including rigid object drop and collision, cloth draping and swinging, and liquid flow, demonstrate that GPT4Motion can generate high-quality videos efficiently in maintaining motion coherency and entity consistency. GPT4Motion offers new insights in text-to-video research, enhancing its quality and broadening its horizon for future explorations.

翻译：近期文本到视频生成技术的进展借助扩散模型的力量，能够基于文本提示生成视觉上引人入胜的内容。然而，这些方法通常面临计算成本高、难以生成具有连贯物理运动的视频等问题。针对这些挑战，我们提出GPT4Motion——一种无需训练的框架，通过结合大型语言模型（如GPT）的规划能力、Blender的物理模拟优势以及文本到图像扩散模型卓越的图像生成能力，来提升视频合成质量。具体而言，GPT4Motion利用GPT-4根据用户文本提示生成Blender脚本，该脚本调用Blender内置物理引擎构建包含帧间连贯物理运动的基础场景组件；随后将这些组件输入Stable Diffusion，生成与文本提示对齐的视频。在刚体下落与碰撞、布料垂坠与摆动、液体流动三种基础物理运动场景上的实验结果表明，GPT4Motion能够高效生成高质量视频，并在保持运动连贯性与实体一致性方面表现出色。GPT4Motion为文本到视频研究提供了新思路，提升了视频质量，拓宽了未来探索的视野。