VisionXLab/FIRM-Video download history
VisionXLab/FIRM-Video is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 386 times (63 in the last 7 days), and 550 times in total. It ranks #40,449 among datasets by monthly downloads.
FIRM-Video-SFT-90K This repository releases the 90K SFT data for FIRM-Video. The dataset covers three key evaluation dimensions: Instruction Following (IF): whether the generated video accurately follows the text prompt. Visual Quality (VQ): perceptual and technical quality, includin