Text-to-Video
50 results
MultimodalTextVideo
Vript_Chinese
🎬 Vript: Refine Video Captioning into Video Scripting Github Repo We construct a fine-grained video-text dataset with 44.7K…
100K–1M·JSON
ImageMultimodalText
VideoThinkBench
CVPR 2026 Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm 🎊 News 2026.02 🔥🔥Our work…
1K–10K·MIT·Parquet
MultimodalTabularText
Talker-T2AV-Data
Talker-T2AV-Data Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling Paper (arXiv 2604.23586) · Code (GitHub) · Model ·…
100K–1M·Apache-2.0·CSV
Image
UniVA-Bench
UniVA-Bench Paper: UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist Project Page: Code: UniVA-Bench is a…
1K–10K·Images (folder)
MultimodalTabularText
MSR-VTT
Clone from "friedrichor/MSR-VTT". MSRVTT contains 10K video clips and 200K captions. We adopt the standard 1K-A split protocol,…
10K–100K·JSON
MultimodalTabularText
Wan2.2-Syn-121x704x1280_32k
FastVideo Synthetic Wan2.2 720P dataset FastVideo Team Paper Github Project Page Abstract Scaling video diffusion transformers (DiTs) is…
10K–100K·Apache-2.0
MultimodalTabularText
Wan2.2-Syn-121x704x1280_32k
FastVideo Synthetic Wan2.2 720P dataset FastVideo Team Paper Github Project Page Abstract Scaling video diffusion transformers (DiTs) is…
10K–100K·Apache-2.0·Parquet
MultimodalTextVideo
phyworldbench
PhyWorldBench This repository hosts the core assets of PhyWorldBench, the 1,050 JSON prompt files, the evaluation standards, and…
<1K·MIT·Parquet
ImageMultimodalTabular
Image-to-Video Quality-Scored Clips
Image-to-Video Quality-Scored Clips
1K–10K·CC-BY·JSON
ImageMultimodalText
AVGen-Bench
AVGen-Bench Generated Videos Data Card Overview This data card describes the generated audio-video outputs stored directly in the…
1K–10K·MIT·Parquet
MultimodalTextVideo
CultureScore
CULTURESCORE: Evaluating Cultural Faithfulness in Video Generation Models Dataset Summary CultureScore is a benchmark dataset for evaluating cultural…
1K–10K·CC-BY
Video
openvid-wantrack-processed
OpenVid-WanTrack — preprocessed training data Preprocessed (FastVideo parquet) data used to train the TrackWan point-track-conditioned video model.…
Apache-2.0