← Back to all generators

lucataco/ace-step

A Step Towards Music Generation Foundation Model text2music

Capabilities

Seed

Cost

Community model (estimated from hardware time)

Input Parameters

tagsrequiredstring

Text prompts to guide music generation, e.g., 'epic,cinematic'

durationnumber

Duration of the generated audio in seconds. -1 means a random duration between 30 and 240 seconds.

Default: 60min: 1, max: 240
granularity_scalenumber

Omega scale for APG guidance, or similar for other CFG types.

Default: 10min: -100, max: 100
guidance_intervalnumber

Guidance interval.

Default: 0.5min: 0, max: 1
guidance_interval_decaynumber

Guidance interval decay.

Default: 0min: 0, max: 1
guidance_scalenumber

Overall guidance scale.

Default: 15min: 0, max: 30
guidance_typestring

Guidance type for CFG.

Default: "apg"
apgcfgcfg_star
lyric_guidance_scalenumber

Guidance scale for lyrics.

Default: 0min: 0, max: 10
lyricsstring

Lyrics for the music. Use [verse], [chorus], and [bridge] to separate different parts of the lyrics. Use [instrumental] or [inst] to generate instrumental music

min_guidance_scalenumber

Minimum guidance scale.

Default: 3min: 0, max: 100
number_of_stepsinteger

Number of inference steps.

Default: 60min: 10, max: 200
schedulerstring

Scheduler type.

Default: "euler"
eulerheun
seedinteger

Random seed. Set to -1 to randomize.

Default: -1
tag_guidance_scalenumber

Guidance scale for tags (text prompt).

Default: 0min: 0, max: 10
Version: 280fc4f9ee50Updated: 7/25/2026107.5K runs