jaswon / osu-dreamer
a diffusion-based ML model for generating osu! maps from raw audio
Why this job: matched by what the repo talks about: diffusion, model, bas, generat
What it does
At the end of every epoch, the model parameters will be checkpointed to runs/latent/version_{NUM}/checkpoints/epoch={EPOCH}-step={STEP}.ckpt. You can resume training from a saved checkpoint by adding --ckpt-path [PATH TO CHECKPOINT] to the fit-latent command.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 months ago
- Stars
- 146
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v8.0
- Released 3 months ago
- Built with
- Python
- 98% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 50% closed
- 5 still open
- Pull requests
- 3 merged
- 0 waiting
- Releases
- 21
- 2 in the last year
- No contributing guide
- No security policy
- No code of conduct
More: languages, topics and project record
Languages
- Python 98%
- Batchfile 1%
- Dockerfile <1%
Topics
- beatmap-creator
- beatmap-parser
- machine-learning
- osu
- osugame
- torch
Project record
- JobImage generation
- StatusListed
- Commits739
- Forks12
- Watching4
- Stars in 28 days+1
- CreatedNov 19, 2022
- First seen by usNov 7, 2026
- CheckedNov 8, 2026