You can deploy this model and start earning money today!

ai-forever/
kandinsky-video-motion-predictor

Name: kandinsky-video-motion-predictor
Availability: InStock

safetensors

OpenGVLab/VideoMAEv2-Base

finetune

Views

No views yet

Code: https://github.com/gen-ai-team/kandinsky-video-tools

Demo:

python

from models import VideoMotionPredictor

video_path = "../assets/examples/mixed/girl-listens-to-music-and-dances-happily[mixkit].mp4"

model = VideoMotionPredictor.from_pretrained("ai-forever/kandinsky-video-motion-predictor").to("cuda")
pred_dict = model.inference(video_path, return_dict=True)