Readme
Refer to the GitHub repository for more information.
nateraw
/
video-llava
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
Run time and cost
This model costs approximately $0.0060 to run on Replicate, or 166 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A40 (Large) GPU hardware. Predictions typically complete within 9 seconds. The predict time for this model varies significantly based on the inputs.