comet-ml/kangas
Visualize large-scale multimedia datasets
View on index · View in 3D Map
Related repos
- Multimodal foundation models for video understanding
- Generates minutes-long videos from text and images
- audio foundation model for understanding, generation, and conversation
- Infrastructure for building video analytics pipelines
- Traces and evaluates LLM applications
- Visualizes Tesla dashcam footage with telemetry data in browsers
- AI model for generating human videos from text, images, or audio
- Generates avatars from audio at 45 FPS
- visualize huge datasets as images with Python
- Turn images into cinematic videos with 33 facial expressions and 400+ motion combinations
