Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation
MovieGrid arranges long videos on spatial grids during post-training, generating 6.05x more shots than temporal packing with state-of-the-art cross-shot consistency.
MovieGrid is a multi-grid post-training paradigm that decomposes long videos into temporally ordered chunks arranged on a spatial grid for joint modeling, enabling cross-chunk information exchange. The authors build the Multi-Grid Long Video (MGLV) dataset from 1,000 long-form videos, producing 54K grid videos paired with character-aware story prompts. Under the same token budget, MovieGrid generates 6.05x more shots than Temporal Packing in a 1,616-frame video. It achieves state-of-the-art intra-shot consistency of 0.9131 versus 0.8086 for HoloCine and inter-shot consistency of 0.5914 versus 0.5384 for StoryMem.
- Decomposes long videos into chunks arranged on spatial grids for joint modeling during post-training
- MGLV dataset: 54K grid videos from 1,000 long-form videos with character-aware story prompts
- Generates 6.05x more shots than Temporal Packing under the same token budget
- State-of-the-art intra-shot consistency 0.9131 versus HoloCine 0.8086
From the original article
1 min read at huggingface.co
Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across shots. Existing video generators favor continuous motion and struggle to present complete shot sets when an entire narrative is packed along one temporal axis.
By Jiawei Mao, Haoqin Tu, Hardy Chen · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.