OpenLEAF: A Novel Benchmark for Open-Domain Interleaved Image-Text Generation

J An, Z Yang, L Li, J Wang, K Lin, Z Liu… - Proceedings of the …, 2024 - dl.acm.org
We introduce OpenLEAF, a new benchmark designed for the emerging open-domain
interleaved image-text generation task. This task aims to generate arbitrarily interleaved …

Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training

Z Zhou, J An, J Luo - arxiv preprint arxiv:2412.06029, 2024 - arxiv.org
Precise camera pose control is crucial for video generation with diffusion models. Existing
methods require fine-tuning with additional datasets containing paired videos and camera …