VideoCrafter1: Open Diffusion Models for High-Quality Video Generation
This provides open-source tools for researchers and engineers to advance video generation technology, though it is incremental in offering new models within an existing paradigm.
The authors tackled the problem of limited open-source models for high-quality video generation by introducing two diffusion models: a text-to-video model that generates realistic videos at 1024x576 resolution, outperforming other open-source models, and an image-to-video model that preserves content from a reference image, being the first open-source foundation model of its kind.
Video generation has increasingly gained interest in both academia and industry. Although commercial tools can generate plausible videos, there is a limited number of open-source models available for researchers and engineers. In this work, we introduce two diffusion models for high-quality video generation, namely text-to-video (T2V) and image-to-video (I2V) models. T2V models synthesize a video based on a given text input, while I2V models incorporate an additional image input. Our proposed T2V model can generate realistic and cinematic-quality videos with a resolution of $1024 \times 576$, outperforming other open-source T2V models in terms of quality. The I2V model is designed to produce videos that strictly adhere to the content of the provided reference image, preserving its content, structure, and style. This model is the first open-source I2V foundation model capable of transforming a given image into a video clip while maintaining content preservation constraints. We believe that these open-source video generation models will contribute significantly to the technological advancements within the community.