andreasjansson/musicgen-looper

Generate fixed-bpm loops from text prompts

Capabilities

SeedTop-P

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt`*	string	A description of the music you want to generate.	`—`	—
`bpm`	number	Tempo in beats per minute	`140`	min: 40, max: 300
`classifier_free_guidance`	integer	Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.	`3`	—
`max_duration`	integer	Maximum duration of the generated loop in seconds.	`8`	min: 2, max: 20
`model_version`	string	Model to use for generation. .	`"medium"`	mediumlarge
`output_format`	string	Output format for generated audio.	`"wav"`	wavmp3
`seed`	integer	Seed for random number generator. If None or -1, a random seed will be used.	`-1`	—
`temperature`	number	Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity.	`1`	—
`top_k`	integer	Reduces sampling to the k most likely tokens.	`250`	—
`top_p`	number	Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used.	`0`	—
`variations`	integer	Number of variations to generate	`4`	min: 1, max: 20

promptrequiredstring

A description of the music you want to generate.

bpmnumber

Tempo in beats per minute

Default: 140min: 40, max: 300

classifier_free_guidanceinteger

Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.

Default: 3

max_durationinteger

Maximum duration of the generated loop in seconds.

Default: 8min: 2, max: 20

model_versionstring

Model to use for generation. .

Default: "medium"

mediumlarge

output_formatstring

Output format for generated audio.

Default: "wav"

wavmp3

seedinteger

Seed for random number generator. If None or -1, a random seed will be used.

Default: -1

temperaturenumber

Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity.

Default: 1

top_kinteger

Reduces sampling to the k most likely tokens.

Default: 250

top_pnumber

Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used.

Default: 0

variationsinteger

Number of variations to generate

Default: 4min: 1, max: 20

Version: f8140d0457c2Updated: 7/25/202660.7K runs