music yue2 工作流
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality Give it lyrics (slot1) and a style prompt (positive prompt): it writes a melody-and-chord plan, then realizes that plan as a complete song with vocals and accompaniment. prompts are written like this; /wf /run:music-yue2 (style of your music) /slot1:(lyrics of your music) length set in seconds with /length: caps the length of your song but does not strictly set the actual duration of the song, it will find a natural resolution to the composition by itself. you can place [chorus][intro][outro][bridge][prechorus] lyrical structure tags inside of slot1 NB Workflow will return a lossless image barcode, decode it here https://unlimitedediting.github.io/ComfyUI-YuE2Fast/ there you can adjust the notation of the music and rearrange the score, diffusion is purely for style reply to a png to use that score for a new generation, ensure your png file is NOT compressed or the score data will be corrupted set /slot6:1 for epic orchestral scores
兼容 / 可用于 Graydient 支持的应用
选项
| 选项 | 映射到 | 默认 |
|---|---|---|
(prompt) | Prompt text | — |
/run:music-yue2 | Workflow shortcode | music-yue2 |
使用的模型
music yue2 模型由 ModelTrends 通过短代码 /run:music-yue2 导入 在 ModelTrends 查看 面向开发者（可选）
API 示例代码。你可以用此工作流构建个人应用。准备部署时请 升级到商务计划。详见 完整渲染 API 文档。
curl https://cloud.graydient.ai/api/v3/render/ \
-X POST \
-H "Content-Type: application/vnd.api+json" \
-H "Accept: application/vnd.api+json" \
-H "Authorization: Bearer $GRAYDIENT_TOKEN" \
-d '{
"prompt": "/workflow /run:music-yue2 ",
"callback_url": "https://example.com/webhook/render"
}'这就是幕后工作原理。已经为你配置好了。上表中的参数插入这些槽位，允许你更改工作方式和加载的模型。你无需理解或修改它——它已经设置好，能直接使用。
此工作流页面列出了短代码、选项和 ModelTrends 下载。完整节点图可随工作流下载在 ModelTrends 获得。 此页面尚未绘制该工作流的节点图。请在 ModelTrends 打开以下载工作流文件和加载的模型。
所有工作流：强大工作流程