Downloads · 30 days
113
0% of all-time downloads
kandinsky-video-motion-predictor
ai-forever/kandinsky-video-motion-predictor
kandinsky-video-motion-predictor is a machine learning model from ai-forever. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Code: https://github.com/gen-ai-team/kandinsky-video-tools
All-time downloads
178K
Public
Parameters
115M
461 MB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors461 MB · 100%
At a glance
- Access
- Public
- Created
- Jul 18, 2025
- Updated
- Jul 23, 2025
- SHA
- 347b1a15
Base models
Model card
From the Hugging Face model README
Code: https://github.com/gen-ai-team/kandinsky-video-tools
Demo:
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)
- Created
- Jul 18, 2025
- Updated
- Jul 23, 2025