Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model
This addresses the challenge of generating videos from text and images for AI content creation, but it appears incremental as it builds on existing TI2V methods with a larger model and new benchmark.
The paper tackles the problem of text-driven image-to-video generation by introducing Step-Video-TI2V, a 30B-parameter model that generates videos up to 102 frames, and achieves state-of-the-art performance on a new benchmark.
We present Step-Video-TI2V, a state-of-the-art text-driven image-to-video generation model with 30B parameters, capable of generating videos up to 102 frames based on both text and image inputs. We build Step-Video-TI2V-Eval as a new benchmark for the text-driven image-to-video task and compare Step-Video-TI2V with open-source and commercial TI2V engines using this dataset. Experimental results demonstrate the state-of-the-art performance of Step-Video-TI2V in the image-to-video generation task. Both Step-Video-TI2V and Step-Video-TI2V-Eval are available at https://github.com/stepfun-ai/Step-Video-TI2V.