Project | Checkpoints | Discord
-1 means random duration (30 ~ 240).
Support tags, descriptions, and scene. Use commas to separate different tags.tags and lyrics examples are from ai music generation community
Support lyric structure tags like [verse], [chorus], and [bridge] to separate different parts of the lyrics.Use [instrumental] or [inst] to generate instrumental music. Not support genre structure tag in lyrics
When guidance_scale_lyric > 1 and guidance_scale_text > 1, the guidance scale will not be applied.
Guidance scale for text condition. It can only apply to cfg. set guidance_scale_text=5.0, guidance_scale_lyric=1.5 for start
Seed for the generation
Scheduler type for the generation. euler is recommended. heun will take more time.
CFG type for the generation. apg is recommended. cfg and cfg_star are almost the same.
Use Entropy Rectifying Guidance for tag. It will multiple a temperature to the attention to make a weaker tag condition and make better diversity.
The same but apply to lyric encoder's attention.
The same but apply to diffusion model's attention.
Granularity scale for the generation. Higher values can reduce artifacts
Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)
Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.
Min guidance scale for guidance interval decay's end scale
Optimal Steps for the generation. But not test well
only_lyrics will keep the whole song the same except lyrics difference. Make your diffrence smaller, e.g. one lyrc line change.remix can change the song melody and genre
only_lyrics