Document configurable model paths and v1.1.4

README.md

@@ -1,65 +1,79 @@
 ---
-license: other
+license: cc-by-nc-4.0
 language:
 - zh
 - en
 tags:
-- audio
-- music-generation
 - comfyui
-- voice-conversion
+- music-generation
+- audio
 - yue2
+- transcription
+base_model:
+- mrfakename/YuE2-3B
 ---
 
-# YuE2-Comfy
+# YuE2-Comfy Model Bundle
+
+这是 [ComfyUI YuE2 T8](https://github.com/T8mars/Comfyui-YuE2-T8) 的完整离线模型包，包含 YuE2-3B、YuE2-Vae、SheetSage2、MERT-v2-FullSong、Seed-VC、Demucs 以及离线乐谱渲染资源。
+
+This is the complete offline model bundle for [ComfyUI YuE2 T8](https://github.com/T8mars/Comfyui-YuE2-T8). It contains the generation model, VAE, transcription model, MERT encoder, Seed-VC reference-voice models, Demucs separation model, and offline score renderer assets.
+
+## 放置路径 / Model placement
 
-这是 **T8star-Aix** 为 [Comfyui-YuE2-T8](https://github.com/T8mars/Comfyui-YuE2-T8) 整理并固定验证的离线模型包，供 ComfyUI 节点和 Windows 本地整合包使用。完整模型目录约 **12.23 GiB**。
+通过 ComfyUI Registry 安装 `yue2-t8` 后，默认模型根目录为 `ComfyUI/custom_nodes/yue2-t8/models`。也可以在 WebUI 展开“模型位置与安装说明”选择其他硬盘，或运行 `configure_models.bat`。所选路径本身就是模型根目录，应保持以下结构：
 
-制作者 **By B站UP主：T8star-Aix**
+```text
+ComfyUI/custom_nodes/yue2-t8/models/YuE2-3B/model.safetensors
+ComfyUI/custom_nodes/yue2-t8/models/YuE2-Vae/model.safetensors
+ComfyUI/custom_nodes/yue2-t8/models/SheetSage2/model.safetensors
+ComfyUI/custom_nodes/yue2-t8/models/MERT-v2-FullSong/model.safetensors
+ComfyUI/custom_nodes/yue2-t8/models/SheetSage2/render_assets/
+ComfyUI/custom_nodes/yue2-t8/models/Seed-VC/DiT_seed_v2_uvit_whisper_base_f0_44k_bigvgan_pruned_ft_ema_v2.pth
+ComfyUI/custom_nodes/yue2-t8/models/Demucs/955717e8.safetensors
+ComfyUI/custom_nodes/yue2-t8/models/MODEL_MANIFEST.json
+ComfyUI/custom_nodes/yue2-t8/models/VOICE_MODEL_MANIFEST.json
+```
 
-- GitHub：[T8mars/Comfyui-YuE2-T8](https://github.com/T8mars/Comfyui-YuE2-T8)
-- B站：[T8star-Aix](https://space.bilibili.com/385085361)
-- YouTube：[T8star-Aix](https://www.youtube.com/@T8star-Aix/)
-- 本模型仓库：[t8star/YuE2-Comfy](https://huggingface.co/t8star/YuE2-Comfy)
+If the repository was cloned manually, replace `yue2-t8` with the actual node directory name. Keep all six model directories, both manifests, configuration files, tokenizers, licenses, and renderer assets together. Placing only the weight files in `ComfyUI/models/checkpoints` will not work. The selected path is saved in `settings.json` and is shared by the WebUI and ComfyUI nodes.
 
-## 包含模型
+自动安装：在节点目录运行 `install_runtime.bat`。手动下载示例：
 
-| 目录 | 用途 | 约占空间 |
-| --- | --- | ---: |
-| `YuE2-3B` | 歌词、旋律、和弦和音乐结构生成 | 6.76 GiB |
-| `YuE2-Vae` | 48 kHz 双声道音频解码 | 0.49 GiB |
-| `SheetSage2` | 原曲旋律转谱、ABC/MIDI/乐谱渲染 | 0.22 GiB |
-| `MERT-v2-FullSong` | SheetSage2 音频特征编码 | 2.36 GiB |
-| `Seed-VC` | 零样本参考音色转换，含 Whisper、RMVPE、CAMPPlus 与 BigVGAN | 2.32 GiB |
-| `Demucs` | 原曲人声与伴奏分离 | 0.08 GiB |
+```bash
+hf download t8star/YuE2-Comfy --local-dir ComfyUI/custom_nodes/yue2-t8/models
+```
 
-`MODEL_MANIFEST.json` 与 `VOICE_MODEL_MANIFEST.json` 记录集成所固定的文件大小、来源和 SHA-256。安装脚本下载固定提交后会在本机复验关键权重；正常推理使用离线模式，不会在点击生成时临时联网拉取模型。
+下载到其他硬盘：
 
-## 参考音色翻唱
+```powershell
+.\install_runtime.bat -ModelsDirectory "D:\AI\YuE2-models"
+```
 
-1. 输入原曲或由 YuE2 生成的新歌。
-2. 输入 **1–30 秒**清晰的单人参考干声，推荐 5–25 秒、少混响、无伴奏。
-3. Demucs 分离歌声和伴奏，Seed-VC 按参考音色转换歌声，再混合为 48 kHz 双声道 FLAC。
+## Contents and provenance
 
-可在 WebUI 的“旋律重制 / 参考音色”页面使用，也可在 ComfyUI 中使用 `YuE2 参考音色翻唱` 节点和 `workflows/04_参考音色翻唱.json`。请只使用本人声音或已经取得明确授权的声音。
+| Directory | Upstream repository | Fixed revision | SHA256 of `model.safetensors` |
+| --- | --- | --- | --- |
+| `YuE2-3B` | `mrfakename/YuE2-3B` | `9c7af7677010933b77b159d9dc1a2848c58e26a1` | `1d55c42c1a9875c34f5d736e15078449992b044e807ce2a138e6cf289a1e59e9` |
+| `YuE2-Vae` | `m-a-p/YuE2-Vae` | `95535e72a97bc0f09b8ada125d26b4009428c0e8` | `807ce9d5149fa27c5ad3e6582058469852e908f6c5acc8c8aa338e7ab7751346` |
+| `SheetSage2` | `m-a-p/SheetSage2` | `eab522a8168e8b8b8c4856bf8609cd86198f01fe` | `b235f68091a5f5b644000f2b5acb57d1e70432aca2b34ab1b9cf27236e1f4274` |
+| `MERT-v2-FullSong` | `m-a-p/MERT-v2-FullSong` | `d8ba1c745e733b3908ce6ad16ebeb17ac7600a42` | `e6dd2ab187d6dd62b6521cd7d8f932e237acf0c5757745a7232082e28391350d` |
 
-## 安装
+All four weights were verified against the upstream Git LFS SHA256 values before upload.
 
-推荐按 GitHub README 运行 Windows 一键安装脚本。手动下载时需要保持上述目录名，并把全部内容放到节点根目录的 `models`：
+Seed-VC and Demucs add 24 pinned files listed in `VOICE_MODEL_MANIFEST.json` (2,574,547,539 bytes total). Every file size and SHA256 was verified before upload. Reference-voice cover support uses these files for local vocal separation, voice conversion, and 48 kHz stereo remixing.
 
-```text
-ComfyUI-YuE2/
-└─ models/
-   ├─ YuE2-3B/
-   ├─ YuE2-Vae/
-   ├─ SheetSage2/
-   ├─ MERT-v2-FullSong/
-   ├─ Seed-VC/
-   ├─ Demucs/
-   ├─ MODEL_MANIFEST.json
-   └─ VOICE_MODEL_MANIFEST.json
-```
+## Links
+
+- GitHub node: https://github.com/T8mars/Comfyui-YuE2-T8
+- Latest code-only release: https://github.com/T8mars/Comfyui-YuE2-T8/releases/latest
+- ComfyUI Registry: https://registry.comfy.org/nodes/yue2-t8
+- Bilibili: https://space.bilibili.com/385085361
+- YouTube: https://www.youtube.com/@T8star-Aix/
+- API: https://api.seedance.nz/sign-up?aff=5f4w
+- 在线 AI 应用 / Online AI apps: https://www.runninghub.ai/zh-cn/user-center/1907375370302308353/userPost?inviteCode=rh-v1121
+- ComfyUI 整合包 / Portable package: https://pan.quark.cn/s/264edb7e36bd
+- Hugging Face profile: https://huggingface.co/t8star
 
-## 许可
+## License
 
-这个仓库汇集多个上游项目，**各目录继续适用各自许可**。YuE2 代码和权重采用 CC BY-NC 4.0，仅限非商业用途；Seed-VC 源码和模型采用 GPL-3.0；Whisper 与 CAMPPlus 权重采用 Apache-2.0；RMVPE、BigVGAN 与 Demucs 采用 MIT。模型目录内保留上游 README、LICENSE 或来源说明。下载、使用和分发前请逐项核对适用许可，本仓库不改变任何上游许可。
+YuE2 first-party code and weights use CC BY-NC 4.0 and are limited to non-commercial use. Each model directory includes its license and third-party notices. SheetSage2 and MERT keep their respective upstream license files.