Files
2024-11-05 14:37:40 +00:00

587 lines
34 KiB
JSON

{
"url": "https://replicate.com/meta/musicgen",
"owner": "meta",
"name": "musicgen",
"description": "Generate music from a prompt or melody",
"visibility": "public",
"github_url": "https://github.com/replicate/cog-musicgen",
"paper_url": "https://arxiv.org/abs/2306.05284",
"license_url": "https://github.com/facebookresearch/audiocraft/blob/main/LICENSE_weights",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_featured_image/a921a8b3-3e9e-48ef-995c-29143ea11bec/musicgen.jpeg",
"default_example": {
"id": "soub5pjbe5g5u62q536t73ltku",
"model": "meta/musicgen",
"version": "671ac645ce5e552cc63a54a2bbff63fcf798043055d2dac5fc9e36a837eedcfb",
"status": "succeeded",
"input": {
"top_k": 250,
"top_p": 0,
"prompt": "Edo25 major g melodies that sound triumphant and cinematic. Leading up to a crescendo that resolves in a 9th harmonic",
"duration": 8,
"temperature": 1,
"continuation": false,
"model_version": "stereo-large",
"output_format": "mp3",
"continuation_start": 0,
"multi_band_diffusion": false,
"normalization_strategy": "peak",
"classifier_free_guidance": 3
},
"output": "https://replicate.delivery/pbxt/OeLYIQiltdzMaCex1shlEFy6wuvnvExi0kdjF0gYKEzG5wkSA/out.mp3",
"logs": "Loading model stereo-large...\nDownloading models--facebook--musicgen-stereo-large to models\nDownloaded models--facebook--musicgen-stereo-large in 9.88s\nModel stereo-large loaded successfully.\nUsing seed 187926229\n1 / 400\n2 / 400\n3 / 400\n4 / 400\n5 / 400\n6 / 400\n7 / 400\n8 / 400\n9 / 400\n10 / 400\n11 / 400\n12 / 400\n13 / 400\n14 / 400\n15 / 400\n16 / 400\n17 / 400\n18 / 400\n19 / 400\n20 / 400\n21 / 400\n22 / 400\n23 / 400\n24 / 400\n25 / 400\n26 / 400\n27 / 400\n28 / 400\n29 / 400\n30 / 400\n31 / 400\n32 / 400\n33 / 400\n34 / 400\n35 / 400\n36 / 400\n37 / 400\n38 / 400\n39 / 400\n40 / 400\n41 / 400\n42 / 400\n43 / 400\n44 / 400\n45 / 400\n46 / 400\n47 / 400\n48 / 400\n49 / 400\n50 / 400\n51 / 400\n52 / 400\n53 / 400\n54 / 400\n55 / 400\n56 / 400\n57 / 400\n58 / 400\n59 / 400\n60 / 400\n61 / 400\n62 / 400\n63 / 400\n64 / 400\n65 / 400\n66 / 400\n67 / 400\n68 / 400\n69 / 400\n70 / 400\n71 / 400\n72 / 400\n73 / 400\n74 / 400\n75 / 400\n76 / 400\n77 / 400\n78 / 400\n79 / 400\n80 / 400\n81 / 400\n82 / 400\n83 / 400\n 84 / 400\n85 / 400\n86 / 400\n87 / 400\n88 / 400\n89 / 400\n90 / 400\n91 / 400\n92 / 400\n93 / 400\n94 / 400\n95 / 400\n96 / 400\n97 / 400\n98 / 400\n99 / 400\n100 / 400\n101 / 400\n102 / 400\n103 / 400\n104 / 400\n105 / 400\n106 / 400\n107 / 400\n108 / 400\n109 / 400\n110 / 400\n111 / 400\n112 / 400\n113 / 400\n114 / 400\n115 / 400\n116 / 400\n117 / 400\n118 / 400\n119 / 400\n120 / 400\n121 / 400\n122 / 400\n123 / 400\n124 / 400\n125 / 400\n126 / 400\n127 / 400\n128 / 400\n129 / 400\n130 / 400\n131 / 400\n132 / 400\n133 / 400\n134 / 400\n135 / 400\n136 / 400\n137 / 400\n138 / 400\n139 / 400\n140 / 400\n141 / 400\n142 / 400\n143 / 400\n144 / 400\n145 / 400\n146 / 400\n147 / 400\n148 / 400\n149 / 400\n150 / 400\n151 / 400\n152 / 400\n153 / 400\n154 / 400\n155 / 400\n156 / 400\n157 / 400\n158 / 400\n159 / 400\n160 / 400\n161 / 400\n162 / 400\n163 / 400\n164 / 400\n165 / 400\n166 / 400\n167 / 400\n168 / 400\n169 / 400\n170 / 400\n171 / 400\n172 / 400\n173 / 400\n174 / 400\n175 / 400\n176 / 400\n177 / 400\n178 / 400\n179 / 400\n180 / 400\n181 / 400\n182 / 400\n183 / 400\n184 / 400\n185 / 400\n186 / 400\n187 / 400\n188 / 400\n189 / 400\n190 / 400\n191 / 400\n192 / 400\n193 / 400\n194 / 400\n195 / 400\n196 / 400\n197 / 400\n198 / 400\n199 / 400\n200 / 400\n201 / 400\n202 / 400\n203 / 400\n204 / 400\n205 / 400\n206 / 400\n207 / 400\n208 / 400\n209 / 400\n210 / 400\n211 / 400\n212 / 400\n213 / 400\n214 / 400\n215 / 400\n216 / 400\n217 / 400\n218 / 400\n219 / 400\n220 / 400\n221 / 400\n222 / 400\n223 / 400\n224 / 400\n225 / 400\n226 / 400\n227 / 400\n228 / 400\n229 / 400\n230 / 400\n231 / 400\n232 / 400\n233 / 400\n234 / 400\n235 / 400\n236 / 400\n237 / 400\n238 / 400\n239 / 400\n240 / 400\n241 / 400\n242 / 400\n243 / 400\n244 / 400\n245 / 400\n246 / 400\n247 / 400\n248 / 400\n249 / 400\n250 / 400\n251 / 400\n252 / 400\n253 / 400\n254 / 400\n255 / 400\n256 / 400\n257 / 400\n258 / 400\n259 / 400\n260 / 400\n261 / 400\n262 / 400\n263 / 400\n264 / 400\n265 / 400\n266 / 400\n267 / 400\n268 / 400\n269 / 400\n270 / 400\n271 / 400\n272 / 400\n273 / 400\n274 / 400\n275 / 400\n276 / 400\n277 / 400\n278 / 400\n279 / 400\n280 / 400\n281 / 400\n282 / 400\n283 / 400\n284 / 400\n285 / 400\n286 / 400\n287 / 400\n288 / 400\n289 / 400\n290 / 400\n291 / 400\n292 / 400\n293 / 400\n294 / 400\n295 / 400\n296 / 400\n297 / 400\n298 / 400\n299 / 400\n300 / 400\n301 / 400\n302 / 400\n303 / 400\n304 / 400\n305 / 400\n306 / 400\n307 / 400\n308 / 400\n309 / 400\n310 / 400\n311 / 400\n312 / 400\n313 / 400\n314 / 400\n315 / 400\n316 / 400\n317 / 400\n318 / 400\n319 / 400\n320 / 400\n321 / 400\n322 / 400\n323 / 400\n324 / 400\n325 / 400\n326 / 400\n327 / 400\n328 / 400\n329 / 400\n330 / 400\n331 / 400\n332 / 400\n333 / 400\n334 / 400\n335 / 400\n336 / 400\n337 / 400\n338 / 400\n339 / 400\n340 / 400\n341 / 400\n342 / 400\n343 / 400\n344 / 400\n345 / 400\n346 / 400\n347 / 400\n348 / 400\n349 / 400\n350 / 400\n351 / 400\n352 / 400\n353 / 400\n354 / 400\n355 / 400\n356 / 400\n357 / 400\n358 / 400\n359 / 400\n360 / 400\n361 / 400\n362 / 400\n363 / 400\n364 / 400\n365 / 400\n366 / 400\n367 / 400\n368 / 400\n369 / 400\n370 / 400\n371 / 400\n372 / 400\n373 / 400\n374 / 400\n375 / 400\n376 / 400\n377 / 400\n378 / 400\n379 / 400\n380 / 400\n381 / 400\n382 / 400\n383 / 400\n384 / 400\n385 / 400\n386 / 400\n387 / 400\n388 / 400\n389 / 400\n390 / 400\n391 / 400\n392 / 400\n393 / 400\n394 / 400\n395 / 400\n396 / 400\n397 / 400\n398 / 400\n399 / 400\n400 / 400\n401 / 400\n402 / 400\n403 / 400\nffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nGuessed Channel Layout for Input Stream #0.0 : stereo\nInput #0, wav, from 'out.wav':\nMetadata:\nencoder : Lavf58.76.100\nDuration: 00:00:08.00, bitrate: 1024 kb/s\nStream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 32000 Hz, stereo, s16, 1024 kb/s\nStream mapping:\nStream #0:0 -> #0:0 (pcm_s16le (native) -> mp3 (libmp3lame))\nPress [q] to stop, [?] for help\nOutput #0, mp3, to 'out.mp3':\nMetadata:\nTSSE : Lavf58.76.100\nStream #0:0: Audio: mp3, 32000 Hz, stereo, s16p\nMetadata:\nencoder : Lavc58.134.100 libmp3lame\nsize= 0kB time=00:00:00.00 bitrate=N/A speed=N/A\nsize= 95kB time=00:00:07.99 bitrate= 97.1kbits/s speed=45.6x\nvideo:0kB audio:94kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.269717%",
"error": null,
"metrics": {
"predict_time": 66.371701,
"total_time": 66.463286
},
"created_at": "2024-03-28T12:01:08.688755Z",
"started_at": "2024-03-28T12:01:08.780340Z",
"completed_at": "2024-03-28T12:02:15.152041Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/soub5pjbe5g5u62q536t73ltku",
"cancel": "https://api.replicate.com/v1/predictions/soub5pjbe5g5u62q536t73ltku/cancel"
}
},
"latest_version": {
"id": "671ac645ce5e552cc63a54a2bbff63fcf798043055d2dac5fc9e36a837eedcfb",
"created_at": "2024-03-28T11:07:13.003999+00:00",
"cog_version": "0.8.6",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 14,
"description": "Seed for random number generator. If None or -1, a random seed will be used."
},
"top_k": {
"type": "integer",
"title": "Top K",
"default": 250,
"x-order": 9,
"description": "Reduces sampling to the k most likely tokens."
},
"top_p": {
"type": "number",
"title": "Top P",
"default": 0,
"x-order": 10,
"description": "Reduces sampling to tokens with cumulative probability of p. When set to `0` (default), top_k sampling is used."
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 1,
"description": "A description of the music you want to generate."
},
"duration": {
"type": "integer",
"title": "Duration",
"default": 8,
"x-order": 3,
"description": "Duration of the generated audio in seconds."
},
"input_audio": {
"type": "string",
"title": "Input Audio",
"format": "uri",
"x-order": 2,
"description": "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."
},
"temperature": {
"type": "number",
"title": "Temperature",
"default": 1,
"x-order": 11,
"description": "Controls the 'conservativeness' of the sampling process. Higher temperature means more diversity."
},
"continuation": {
"type": "boolean",
"title": "Continuation",
"default": false,
"x-order": 4,
"description": "If `True`, generated music will continue from `input_audio`. Otherwise, generated music will mimic `input_audio`'s melody."
},
"model_version": {
"allOf": [
{
"$ref": "#/components/schemas/model_version"
}
],
"default": "stereo-melody-large",
"x-order": 0,
"description": "Model to use for generation"
},
"output_format": {
"allOf": [
{
"$ref": "#/components/schemas/output_format"
}
],
"default": "wav",
"x-order": 13,
"description": "Output format for generated audio."
},
"continuation_end": {
"type": "integer",
"title": "Continuation End",
"minimum": 0,
"x-order": 6,
"description": "End time of the audio file to use for continuation. If -1 or None, will default to the end of the audio clip."
},
"continuation_start": {
"type": "integer",
"title": "Continuation Start",
"default": 0,
"minimum": 0,
"x-order": 5,
"description": "Start time of the audio file to use for continuation."
},
"multi_band_diffusion": {
"type": "boolean",
"title": "Multi Band Diffusion",
"default": false,
"x-order": 7,
"description": "If `True`, the EnCodec tokens will be decoded with MultiBand Diffusion. Only works with non-stereo models."
},
"normalization_strategy": {
"allOf": [
{
"$ref": "#/components/schemas/normalization_strategy"
}
],
"default": "loudness",
"x-order": 8,
"description": "Strategy for normalizing audio."
},
"classifier_free_guidance": {
"type": "integer",
"title": "Classifier Free Guidance",
"default": 3,
"x-order": 12,
"description": "Increases the influence of inputs on the output. Higher values produce lower-varience outputs that adhere more closely to inputs."
}
}
},
"Output": {
"type": "string",
"title": "Output",
"format": "uri"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"model_version": {
"enum": [
"stereo-melody-large",
"stereo-large",
"melody-large",
"large"
],
"type": "string",
"title": "model_version",
"description": "An enumeration."
},
"output_format": {
"enum": [
"wav",
"mp3"
],
"type": "string",
"title": "output_format",
"description": "An enumeration."
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
},
"normalization_strategy": {
"enum": [
"loudness",
"clip",
"peak",
"rms"
],
"type": "string",
"title": "normalization_strategy",
"description": "An enumeration."
}
}
}
}
}
}