ACE Step Audio Inpaint

URL of the audio file to be inpainted.

Whether the start time is relative to the start or end of the audio.

Options: start, end

start time in seconds for the inpainting process.

Whether the end time is relative to the start or end of the audio.

Options: start, end

end time in seconds for the inpainting process.

Comma-separated list of genre tags to control the style of the generated audio. Can also be supplied as `prompt`.

Lyrics to be sung in the audio. If not provided or if [inst] or [instrumental] is the content of this field, no lyrics will be sung. Use control structures like [verse], [chorus] and [bridge] to control the structure of the song.

Variance for the inpainting process. Higher values can lead to more diverse results.

Check input content for safety. Disabling requires account authorization.

Number of steps to generate the audio.

Random seed for reproducibility. If not provided, a random seed will be used.

Scheduler to use for the generation process.

Options: euler, heun

Type of CFG to use for the generation process.

Options: cfg, apg, cfg_star

Granularity scale for the generation process. 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.

Guidance scale for the generation.

Minimum guidance scale for the generation after the decay.

Tag guidance scale for the generation.

Lyric guidance scale for the generation.