Text-to-image diffusion model for generating high-quality non-photorealistic images
AI music transcription: convert audio to MIDI and sheet music, scan scores, detect song keys
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Freemium
Pricing
Not given
Free: 5 transcription jobs daily. Downloads are one-time purchases: up to 2 pages $2.99, 3–9 pages $5.99, 10+ pages $9.99 for MusicXML + MIDI; Rehearsal Pack with practice MP3s and slow mixes $3 more. Credit packs: $9 unlocks 4 pieces, $19 unlocks 10. Practice Passes: $9.99 for 30 days or $29 for 90
Key features
Text-to-image generation based on textual descriptions
Fine-tuned on approximately 80,000 pony images
User-friendly interface for easy image generation
CLIP-based aesthetic ranking for quality evaluation
Quality scoring mechanism with score tags
CreativeML OpenRAIL license for free use and redistribution
Community engagement and collaborative development
Transcribe audio files (MP3, WAV, FLAC, OGG) to MIDI and sheet music
Scan sheet music PDFs and photos into editable MusicXML
Detect song key, Camelot code and BPM
Browser preview with highlighted notes before downloading
Note-matching exercises with microphone or keyboard input
Harmonic-ghost filter to remove phantom octave notes from transcription
Quality metrics displayed on every transcription job
What makes it different
Specialized for non-photorealistic art and creative styles
Fine-tuned specifically on pony-themed artwork
Open source with commercial use permitted
Tuned transcription engine with harmonic-ghost filter, not an API wrapper
Honest quality metrics on every job showing notes detected and ghosts filtered
Free daily use with no account required
One-time payments per piece, no subscription required
Professional notation engraving and MusicXML output for editing in music software