supplementary document explanation

README.md

@@ -4,6 +4,8 @@
 
 高保真的语音克隆节点, 支持中英文, 并可跨语言克隆.
 
+![workflow](example_workflow/workflow.webp)
+
 ## 更新
 
 [2025-04-16]⚒️: 发布 v1.0.0.
@@ -19,6 +21,27 @@ pip install -r requirements.txt
 
 ## 模型下载
 
+1. [模型MegaTTS3国外](https://huggingface.co/ByteDance/MegaTTS3/tree/main)
+2. [模型MegaTTS3国内](https://www.modelscope.cn/models/ByteDance/MegaTTS3/files)
+3. [音色（用户上传）](https://drive.google.com/drive/folders/1QhcHWcy20JfqWjgqZX1YM3I6i9u4oNlr?usp=sharing)
+
+模型存放目录：models/TTS/MegaTTS3
+```
+├─models
+│  ─TTS
+│  │  ├─MegaTTS3
+│  │  │  ├─aligner_lm
+│  │  │  ├─diffusion_transformer
+│  │  │  ├─duration_lm
+│  │  │  ├─g2p
+│  │  │  ├─Voices # 音色存放目录 wav,npy
+│  │  │  |  └─1.wav
+|  │  |  |  └─1.npy
+│  │  │  └─wavvae
+│  │  ├──config.json
+|  |  └──config.json
+```
+
 
 
 ## 鸣谢

node.py

@@ -113,5 +113,5 @@ NODE_CLASS_MAPPINGS = {
 
 NODE_DISPLAY_NAME_MAPPINGS = {
     "AVMegaTTS3": "AV Mega TTS3",
-    "AVPromptInit": "Prompt Init",
+    "AVPromptInit": "AV Prompt Init",
 }

pyproject.toml

@@ -1,7 +1,7 @@
 [project]
 name = "ComfyUI-AV-MegaTTS3"
 description = "🎧Ultra High-Quality Voice Cloning, Chinese and English."
-version = "1.0.0"
+version = "1.0.1"
 license = {file = "LICENSE"}
 dependencies = ["setproctitle", "attrdict", "librosa", "pydub", "pyloudnorm", "x-transformers", "torchdiffeq", "openai-whisper>=20240930", "torch>=2.0.0"]