cinemasetfree.com
meta/musicgen
Generate music from a prompt or melody
Capabilities
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
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 | — |
continuation | boolean | If `True`, generated music will continue from `input_audio`. Otherwise, generated music will mimic `input_audio`'s melody. | false | — |
continuation_end | integer | End time of the audio file to use for continuation. If -1 or None, will default to the end of the audio clip. | — | min: 0 |
continuation_start | integer | Start time of the audio file to use for continuation. | 0 | min: 0 |
duration | integer | Duration of the generated audio in seconds. | 8 | — |
input_audio | string(uri) | An audio file that will influence the generated music. If `continuation` is `True`, the generated music will be a continuation of the audio file. Otherwise, the generated music will mimic the audio file's melody. | — | — |
model_version | string | Model to use for generation | "stereo-melody-large" | stereo-melody-largestereo-largemelody-largelarge |
multi_band_diffusion | boolean | If `True`, the EnCodec tokens will be decoded with MultiBand Diffusion. Only works with non-stereo models. | false | — |
normalization_strategy | string | Strategy for normalizing audio. | "loudness" | loudnessclippeakrms |
output_format | string | Output format for generated audio. | "wav" | wavmp3 |
prompt | string | A description of the music you want to generate. | — | — |
seed | integer | Seed for random number generator. If None or -1, a random seed will be used. | — | — |
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 | — |
classifier_free_guidanceintegerIncreases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs.
3continuationbooleanIf `True`, generated music will continue from `input_audio`. Otherwise, generated music will mimic `input_audio`'s melody.
falsecontinuation_endintegerEnd time of the audio file to use for continuation. If -1 or None, will default to the end of the audio clip.
continuation_startintegerStart time of the audio file to use for continuation.
0min: 0durationintegerDuration of the generated audio in seconds.
8input_audiostringAn audio file that will influence the generated music. If `continuation` is `True`, the generated music will be a continuation of the audio file. Otherwise, the generated music will mimic the audio file's melody.
model_versionstringModel to use for generation
"stereo-melody-large"multi_band_diffusionbooleanIf `True`, the EnCodec tokens will be decoded with MultiBand Diffusion. Only works with non-stereo models.
falsenormalization_strategystringStrategy for normalizing audio.
"loudness"output_formatstringOutput format for generated audio.
"wav"promptstringA description of the music you want to generate.
seedintegerSeed for random number generator. If None or -1, a random seed will be used.
temperaturenumberControls the 'conservativeness' of the sampling process. Higher temperature means more diversity.
1top_kintegerReduces sampling to the k most likely tokens.
250top_pnumberReduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used.
0671ac645ce5eUpdated: 7/25/20263.3M runs