AIPeanutman/OmitI2V download history
AIPeanutman/OmitI2V is an image to video dataset on the Hugging Face Hub. In the last 30 days it was downloaded 427 times (8 in the last 7 days), and 1,011 times in total. It ranks #37,468 among datasets by monthly downloads.
OmitI2V OmitI2V is a benchmark for evaluating semantic fidelity (prompt adherence) in text-guided image-to-video (TI2V) generation, focusing on prompts that require substantial edits to the reference image — object addition, deletion, and modification. It is the benchmark introduced i