osu!mania 4K · PyTorch · 6.97M params
ManiaMapper
AI-generated osu!mania 4K beatmaps from any song.
- 127
- training maps
- 4
- difficulties
- 90.1%
- pattern acc.*
*training-set accuracy
02 · Lite demo
Map your own song
Difficulty
Detected BPM
—
Total notes
—
Notes / sec
—
Long notes
—
What the Lite demo does
Spectral flux on 1024-sample frames finds onsets, autocorrelation estimates the BPM, and notes are placed on a 1/4-beat grid above an adaptive threshold tuned to the difficulty's notes-per-second target. Chords go on the strongest hits, long notes on sustained loud passages, and columns are balanced with a 60 ms same-column gap.
Load a song to preview its map
This is a simplified rule-based version. The real ManiaMapper uses a neural network trained on 127 human-made maps to learn patterns, not just onsets.
03 · The real model
How ManiaMapper works
- 01
Audio file
any song - 02
Librosa analysis
BPMbeatsonsetsmel spectrogramchromaspectral features - 03
Beat grid
time steps aligned to beats - 04
Encoder + Decoder
mania_model.ptdifficulty-conditionedautoregressive - 05
Note assignment
column selectionmin-gaprebalancing - 06
Speed variation
optional - 07
.osu writer
timing + hit objects - 08
.osz package
ready to import
Architecture
~6.97M parameters- Input
(B, T, 130) = 114 audio features + 16 cross-difficulty context
Difficulty embedding: 4 levels → 32-dim
- Encoder
2 × multi-scale depthwise conv blocks, kernels 3 / 5 / 9 / 13 / 25
4-layer BiLSTM, 384-dim
- Decoder
Causal 2-layer LSTM, 256 hidden
+ 64-dim embedding of the previously placed event
- Heads
Per difficulty: hit (4 columns) · LN start (4) · LN duration (4)
+ 18-class pattern head
04 · Training results
What it learned from
Usable maps
127 / 151 scanned
Easy 14 · Normal 21 · Hard 52 · Insane 40
Training sequences
2,408
of 256 steps each
Regular notes
222,013
hit objects
Long notes
45,807
hold objects
Total loss per epoch
15.64 → 0.30 · log scale
Pattern accuracy per epoch
7.9% → 90.1% · training set
Difficulty presets
| Level | HP | OD | Max chord | Target nps | Target LN % |
|---|---|---|---|---|---|
| Easy | 6 | 6 | 1 | 2.5 | 4% |
| Normal | 7 | 7 | 2 | 4.5 | 7% |
| Hard | 8 | 8 | 2 | 9.5 | 10% |
| Insane | 9 | 9 | 3 | 16.0 | 12% |
Honest limitations
- 90.1% is training-set accuracy — there is no held-out validation split.
- There's no automated playability metric, so map quality is a human judgement.
- 4K only.
- A single documented training run.