From Video Clips to Creation Trajectory: Sora100K for AI-Native Video Creation
In this paper, we introduce Sora100K, a dataset that represents the AI-Native video creation workflow as a structured video creation trajectory.
Key points
- AI-Native video creation is shifting from isolated video clips toward iterative video creation workflows.
- However, existing datasets remain largely video clips, representing video generation and editing as separate tasks rather than connected stages of a video creation workflow.
- Specifically, we first identify video creation trajectories and decompose them into three subsets according to their structural roles: text-to-video generation records as roots, single-turn video editing records as editing edges, and multi-turn video editing records as complete trajectories.
- Finally, we perform lightweight adaptation on LTX-2 models to assess the supervision value of Sora100K.
Sources (1)
- [1]From Video Clips to Creation Trajectory: Sora100K for AI-Native Video CreationarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 11:52 AM
In this paper, we introduce Sora100K, a dataset that represents the AI-Native video creation workflow as a structured video creation trajectory.
AI-Native video creation is shifting from isolated video clips toward iterative video creation workflows.
Extractive summary: sentences quoted from the sources.