Sorry to bother you again, but I'm using this workflow. Which file should I download?

[getlone]

I downloaded the model.safetensors file, but it's not working
https://huggingface.co/IndexTeam/IndexTTS-2/tree/main/qwen0.6bemo4-merge

Workflow https://github.com/diodiogod/TTS-Audio-Suite/blob/main/example_workflows/%F0%9F%8C%88%20IndexTTS-2%20integration.json

E:\AI WOEK\comfy\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
Adding extra search path checkpoints E:\AI WOEK\forge\webui\models\Stable-diffusion
Adding extra search path configs E:\AI WOEK\forge\webui\models\Stable-diffusion
Adding extra search path vae E:\AI WOEK\forge\webui\models\VAE
Adding extra search path loras E:\AI WOEK\forge\webui\models\Lora
Adding extra search path loras E:\AI WOEK\forge\webui\models\LyCORIS
Adding extra search path upscale_models E:\AI WOEK\forge\webui\models\ESRGAN
Adding extra search path upscale_models E:\AI WOEK\forge\webui\models\RealESRGAN
Adding extra search path upscale_models E:\AI WOEK\forge\webui\models\SwinIR
Adding extra search path embeddings E:\AI WOEK\forge\webui\embeddings
Adding extra search path hypernetworks E:\AI WOEK\forge\webui\models\hypernetworks
Adding extra search path controlnet E:\AI WOEK\forge\webui\models\ControlNet
[START] Security scan
[DONE] Security scan

ComfyUI-Manager: installing dependencies done.

** ComfyUI startup time: 2025-09-18 22:11:17.148
** Platform: Windows
** Python version: 3.12.9 (tags/v3.12.9:fdb8142, Feb 4 2025, 15:27:58) [MSC v.1942 64 bit (AMD64)]
** Python executable: E:\AI WOEK\comfy\ComfyUI_windows_portable\python_embeded\python.exe
** ComfyUI Path: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI
** ComfyUI Base Folder Path: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI
** User directory: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\user
** ComfyUI-Manager config path: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Manager\config.ini
** Log path: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
0.0 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
18.0 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager

Checkpoint files will always be loaded safely.
Total VRAM 12288 MB, total RAM 16332 MB
pytorch version: 2.6.0+cu126
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 2060 : cudaMallocAsync
Using pytorch attention
Python version: 3.12.9 (tags/v3.12.9:fdb8142, Feb 4 2025, 15:27:58) [MSC v.1942 64 bit (AMD64)]
ComfyUI version: 0.3.59
ComfyUI frontend version: 1.26.11
[Prompt Server] web root: E:\AI WOEK\comfy\ComfyUI_windows_portable\python_embeded\Lib\site-packages\comfyui_frontend_package\static
Adding E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes to sys.path
Loaded Efficiency nodes from E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui
Could not find ControlNetPreprocessors nodes
Could not find AdvancedControlNet nodes
Could not find AnimateDiff nodes
Could not find IPAdapter nodes
Could not find VideoHelperSuite nodes
Could not load ImpactPack nodes Could not find ImpactPack nodes
ComfyUI-GGUF: Partial torch compile only, consider updating pytorch

Loading: ComfyUI-Impact-Pack (V8.14.2)

[Impact Pack] Wildcards loading done.

Loading: ComfyUI-Impact-Subpack (V1.3.2)

[Impact Pack/Subpack] Using folder_paths to determine whitelist path: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Pack/Subpack] Ensured whitelist directory exists: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack
[Impact Pack/Subpack] Loaded 0 model(s) from whitelist: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\user\default\ComfyUI-Impact-Subpack\model-whitelist.txt
[Impact Subpack] ultralytics_bbox: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\models\ultralytics\bbox
[Impact Subpack] ultralytics_segm: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\models\ultralytics\segm
E:\AI WOEK\comfy\ComfyUI_windows_portable\python_embeded\Lib\site-packages\albumentations_init_.py:28: UserWarning: A new version of Albumentations is available: '2.0.8' (you have '2.0.6'). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1.
check_for_updates()
Total VRAM 12288 MB, total RAM 16332 MB
pytorch version: 2.6.0+cu126
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 2060 : cudaMallocAsync

Loading: ComfyUI-Manager (V3.37)

[ComfyUI-Manager] network_mode: public

ComfyUI Version: v0.3.59-26-gf228367c | Released on '2025-09-13'

[VideoHelperSuite] - WARNING - Failed to import imageio_ffmpeg
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json
[tinyterraNodes] Loaded
Using pytorch attention
(RES4LYF) Init
(RES4LYF) Importing beta samplers.
(RES4LYF) Importing legacy samplers.
Using pytorch attention
(RES4LYF) Init
(RES4LYF) Importing beta samplers.
(RES4LYF) Importing legacy samplers.

[rgthree-comfy] Loaded 42 fantastic nodes. 🎉

🔧 TTS Audio Suite: Python 3.12 - numba JIT enabled
FETCH ComfyRegistry Data: 5/98
ℹ️ Critical package versions: NumPy 1.26.4, Librosa 0.11.0, Numba 0.61.2, PyTorch 2.6.0+cu126, TorchAudio 2.6.0+cu126, Transformers 4.51.3, SoundFile 0.13.1
FETCH ComfyRegistry Data: 10/98
FETCH ComfyRegistry Data: 15/98
✅ ChatterboxTTS loaded from bundled package
✅ ChatterboxVC loaded from bundled package
FETCH ComfyRegistry Data: 20/98
✅ F5-TTS loaded from system package
APEX FusedRMSNorm not available, using native implementation
🎭 Character voices: Found 26 characters, 10 aliases
❌ Vocal/Noise Removal failed: No module named 'audio_separator'

🚀 TTS Audio Suite v4.9.19
Universal multi-engine TTS extension for ComfyUI
✓ Using ComfyUI ChatterBox models
FETCH ComfyRegistry Data: 25/98
Loading faiss with AVX2 support.
Successfully loaded faiss with AVX2 support.
📋 System Dependencies:
⚠️ Engine dependencies missing:
Higgs Audio 2:
• descript-audio-codec (import: dac)
RVC Voice Conversion:
• torchcrepe (import: torchcrepe)
🔧 Fix: pip install -r requirements.txt
ℹ️ Engine nodes will fail without dependencies
✅ TTS Audio Suite v4.9.19 loaded with 23 nodes:
• ⚙️ ChatterBox Official 23-Lang Engine
• ⚙️ ChatterBox TTS Engine
• ⚙️ F5 TTS Engine
• ⚙️ Higgs Audio 2 Engine
• ⚙️ IndexTTS-2 Engine
• ⚙️ RVC Engine
• ⚙️ VibeVoice Engine
• 🌈 IndexTTS-2 Emotion Vectors
• 🌈 IndexTTS-2 Text Emotion
• 🌊 Audio Wave Analyzer
• 🎙️ Voice Capture
• 🎤 TTS Text
• 🎭 Character Voices
• 🎭 Load RVC Character Model
• 👄 F5-TTS Speech Editor
• 📺 TTS SRT
• 🔄 Voice Changer
• 🔧 Audio Analyzer Options
• 🔧 F5-TTS Edit Options
• 🔧 RVC Pitch Extraction Options
• 🔧 Viseme Mouth Shape Options
• 🗣️ Silent Speech Analyzer
• 🥪 Merge Audio

Import times for custom nodes:
0.0 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\efficiency-nodes-comfyui
0.0 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_bnb_nf4_fp4_Loaders
0.0 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\websocket_image_save.py
0.0 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Notifications
0.0 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\cg-use-everywhere-main
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-inpaint-cropandstitch
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_zenid
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\teacache
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_UltimateSDUpscale
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI_essentials-main
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Custom-Scripts
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfy-image-saver
0.1 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_instantid
0.2 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_essentials
0.2 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-GGUF
0.2 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-KJNodes-main
0.3 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy
0.3 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-kjnodes
0.3 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite-main
0.6 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-pack
0.8 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_tinyterranodes
1.2 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-manager
1.2 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\RES4LYF-main
1.5 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\RES4LYF
1.7 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-art-venture
5.5 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui-impact-subpack
15.4 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-InstantID
28.3 seconds: E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite

Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://127.0.0.1:8188
FETCH ComfyRegistry Data: 30/98
FETCH ComfyRegistry Data: 35/98
FETCH ComfyRegistry Data: 40/98
Exception in callback _ProactorBasePipeTransport._call_connection_lost(None)
handle: <Handle _ProactorBasePipeTransport._call_connection_lost(None)>
Traceback (most recent call last):
File "asyncio\events.py", line 88, in _run
File "asyncio\proactor_events.py", line 165, in _call_connection_lost
ConnectionResetError: [WinError 10054] An existing connection was forcibly closed by the remote host
FETCH ComfyRegistry Data: 45/98
FETCH ComfyRegistry Data: 50/98
FETCH ComfyRegistry Data: 55/98
got prompt
💬 Narrator Voice: David_Attenborough CC3 ready for F5-TTS, ChatterBox, and future engines (text from voices_examples/David_Attenborough CC3.wav)
🎭 IndexTTS-2 Emotion Vectors: {'happy': 0.17, 'angry': 0.29, 'sad': 0.86, 'surprised': 0.61, 'afraid': 0.94, 'disgusted': 0.15, 'calm': 0.05, 'melancholic': 0.31}
⚙️ IndexTTS-2: Configured on auto
Model: IndexTTS-2
Emotion: alpha=0.7, use_text=False
Generation: temp=0.8, top_p=0.8, top_k=30
Chunking: max_tokens=120, silence=200ms
🎤 TTS Text: Using voice reference from Character Voices node (David_Attenborough CC3)
🎤 Generating Index_Tts for 'David_Attenborough CC3' (lang: en)
✅ IndexTTS-2 adapter initialized with model at: IndexTTS-2
🤖 IndexTTS-2: Processing text with emotion support
📝 IndexTTS-2: Using native token chunking (120 tokens), disabling character chunking
🎭 IndexTTS-2: Processing 3 character segment(s) - narrator
📖 Using connected narrator voice | Ref: 'The first one who physical contact was with a fema...'
🎭 No emotion audio for simple text segment (no connected engine emotion)
FETCH ComfyRegistry Data: 60/98
🔄 IndexTTS-2: Initializing engine (first run may take 2-3 minutes to load models)...
Loading: QwenEmotion → GPT → Semantic Codec → S2Mel → CampPlus → BigVGAN...
❌ IndexTTS-2 processor error: IndexTTS-2 model not found at E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\models\TTS\IndexTTS\IndexTTS-2
Traceback (most recent call last):
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\engines\processors\index_tts_processor.py", line 410, in process_text
result = self.pause_processor.generate_audio_with_pauses(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\utils\text\pause_processor.py", line 126, in generate_audio_with_pauses
audio = tts_generate_func(content, **generation_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\engines\processors\index_tts_processor.py", line 376, in tts_generate_func
result = self.adapter.generate(
^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\engines\adapters\index_tts_adapter.py", line 265, in generate
audio = self.engine.generate(
^^^^^^^^^^^^^^^^^^^^^
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\engines\index_tts\index_tts.py", line 177, in generate
self._ensure_model_loaded()
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\engines\index_tts\index_tts.py", line 117, in _ensure_model_loaded
self._tts_engine = unified_model_interface.load_model(self._model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\utils\models\unified_model_interface.py", line 164, in load_model
wrapper = tts_model_manager.load_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\utils\models\comfyui_model_wrapper\model_manager.py", line 233, in load_model
model = model_factory_func(**factory_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\custom_nodes\tts_audio_suite\utils\models\unified_model_interface.py", line 642, in index_tts_factory
raise RuntimeError(f"IndexTTS-2 model not found at {model_path}")
RuntimeError: IndexTTS-2 model not found at E:\AI WOEK\comfy\ComfyUI_windows_portable\ComfyUI\models\TTS\IndexTTS\IndexTTS-2
✅ Index_Tts generation complete. Default narrator: David_Attenborough CC3
Prompt executed in 1.96 seconds
FETCH ComfyRegistry Data: 65/98
FETCH ComfyRegistry Data: 70/98
FETCH ComfyRegistry Data: 75/98
FETCH ComfyRegistry Data: 80/98
FETCH ComfyRegistry Data: 85/98
FETCH ComfyRegistry Data: 90/98
FETCH ComfyRegistry Data: 95/98
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.

[getlone]

I hope this is the last issue I need to deal with.

[diodiogod]

Why don't you let the node auto-download the model for you? Your download is probably incomplete. Just delete the folder and run the workflow.
Also the init log shows some dependencies missing, did you install it through the manager? Did the install.py script run?

[getlone]

through the manager

[diodiogod]

Also, this is the discussion Forum, not the issue tab. I won't be looking here too much.