Recognize faces in a live video stream
remove background from any image
I scrape web articles
Swap faces in photos and videos
Anonymize and resynthesize speech from your recording
Create animated videos using a reference image and motion sequence
Find choruses in music from YouTube or uploaded MP3 files
Generate a 2-speaker podcast from text input or documents!
Validate JSONL format for fine-tuning
Separe vocal and instrumental tracks from audio
Upload an image, detect objects, hear descriptions
Generate answers to user questions
Generate sentiment analysis for YouTube comments
Enhance and clean videos by removing watermarks and upscaling
Enhance video quality by uploading and processing
Generate music with chord progression and MIDI prompts
Try CANVAS-S in this huggingface space
Ask questions about scientific papers
Which Emoji fits the English Text?
Separate vocals from audio/video files