ConditionVideo: Training-Free Condition-Guided Video Generation

Authors: Bo Peng, Xinyuan Chen, Yaohui Wang, Chaochao Lu, Yu Qiao

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 5 Experiments, 5.1 Implementation Details, 5.2 Main results, 5.3 Comparison, 5.4 Ablation Study
Researcher Affiliation Collaboration Bo Peng1,2*, Xinyuan Chen2 , Yaohui Wang2, Chaochao Lu2, Yu Qiao2 1Shanghai Jiao Tong University 2Shanghai Artificial Intelligence Laboratory {pengbo,chenxinyuan,wangyaohui,luchaochao,qiaoyu}@pjlab.org.cn
Pseudocode Yes Algorithm 1: Sampling Algorithm
Open Source Code No For the project website, see https://pengbo807.github.io/conditionvideo-website/
Open Datasets No The paper states "The conditions are randomly generated from a group of 120 different videos" and mentions fine-tuning on videos, but provides no concrete access information (link, DOI, repository, or formal citation) for these datasets.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or detailed splitting methodology).
Hardware Specification No No specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running experiments are provided.
Software Dependencies No The paper mentions "Stable Diffusion 1.5" but does not provide specific software dependencies (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9) needed to replicate the experiment.
Experiment Setup Yes We generate 24 frames with a resolution of 512 × 512 pixels for each video. During inference, we use the same sampling setting as Tune-A-Video (Wu et al. 2022b).