video_understand

Tools · A check on the result · AGPL-3.0 · Link only

Here to learn from. We link to it and do not hand you its code.

What it does

Describes frames or clips with a local vision-language model. Runs on your own GPU with model weights you download; needs transformers, torch. Needs a key, a program or a download before it works.

From

OpenMontage

Everything from OpenMontage in the gallery

Back to the Asset Library