Video Edit
Total_Editing_Synthetic_Video_Albedo_FullFiVE-Fine-Grained-Video-Editing-Benchmark
FiVE-Bench
FiVE-Bench: A Fine-Grained Video Editing Benchmark for Evaluating Diffusion and Rectified Flow Models
Minghan Li1*, Chenxi Xie2*, Yichen Wu13, Lei Zhang2, Mengyu Wang1†
1Harvard University 2The Hong Kong Polytechnic University 3City University of Hong Kong
*Equal contribution †Corresponding Author
💜 Leaderboard (coming soon) |
💻 GitHub |
🤗 Hugging Face
📝 Project Page |
📰 Paper |
🎥 Video Demo
FiVE is a benchmark comprising 100 videos for… See the full description on the dataset page: https://huggingface.co/datasets/LIMinghan/FiVE-Fine-Grained-Video-Editing-Benchmark.wan2.7-videoedit-resultspremiere-video-editing-trajectories
Creative Video-Editing Computer-Use Trajectories (Preview)
A preview release of computer-use agent trajectories from professional video-editing work in Adobe Premiere Pro (building vertical short-form social reels). Each step pairs a screenshot with a structured action and a first-person thought grounded in the editor's spoken narration as they worked, so the step-level reasoning reflects real human intent rather than a rationale written after the fact.
A sample of the human… See the full description on the dataset page: https://huggingface.co/datasets/contralabs/premiere-video-editing-trajectories.video-editor-cudah3-video-edit-showcase
MiniMax-H3 video edit showcase
30 edits across 5 source clips, generated with MiniMax-H3 ref2va. Each output
is a 5.16 s / 124-frame segment at 832×480, produced from the source clip plus a
hand-written six-section prompt. Nothing here is cherry-picked: every edit
attempted is included, including the ones that did not work.
Generated on a single NVIDIA B200 at 3.5 min per edit — 105 min for the set.
The same work takes 13–19 min per edit on an RTX PRO 6000 (sm_120), the… See the full description on the dataset page: https://huggingface.co/datasets/consciousengines/h3-video-edit-showcase.