The recent update has caused issues with audio output on Ace-step 1.5 using XPU.

### Custom Node Testing

- [x] I have tried disabling custom nodes and the issue persists (see [how to disable custom nodes](https://docs.comfy.org/troubleshooting/custom-node-issues#step-1%3A-test-with-all-custom-nodes-disabled) if you need help)

### Expected Behavior

The recent update has unfortunately caused issues with the audio output on Ace-step 1.5, resulting in no sound being produced.

### Actual Behavior

The official ComfyUI workflow, which previously produced sound, now produces output without sound despite using the same starting parameters as before.

I'm using the same command to launch ComfyUI as before, but I had to include the `--gpu-only` flag to ensure it processes on the GPU. It worked well previously, but after the update, it seems to default to CPU processing.

see the .bat below;

### Steps to Reproduce

@echo off
title ComfyUI - Intel Arc 140v (Speed Recovery)

echo ================================================
echo Starting ComfyUI with Intel Arc XPU
echo ================================================

:: They don't affect math, just driver stability.
set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
set SYCL_CACHE_PERSISTENT=1

cd /d C:\ComfyUI
call comfyui_venv\Scripts\activate.bat

:: We removed --use-pytorch-cross-attention
:: We kept your original --gpu-only and --cache-none
python main.py ^
--gpu-only ^
--cache-none ^
--front-end-version "Comfy-Org/ComfyUI_frontend@latest" ^
--enable-cors-header "*" ^
--listen 0.0.0.0

pause

### Debug Logs

```powershell
## ComfyUI-Manager: installing dependencies done.
** ComfyUI startup time: 2026-02-04 18:35:13.360
** Platform: Windows
** Python version: 3.11.0 (main, Oct 24 2022, 18:26:48) [MSC v.1933 64 bit (AMD64)]
** Python executable: C:\ComfyUI\comfyui_venv\Scripts\python.exe
** ComfyUI Path: C:\ComfyUI\custom_nodes\comfyui-impact-pack/../../
** ComfyUI Base Folder Path: C:\ComfyUI\custom_nodes\comfyui-impact-pack/../../
** User directory: C:\ComfyUI\user
** ComfyUI-Manager config path: C:\ComfyUI\user\__manager\config.ini
** Log path: C:\ComfyUI\user\comfyui.log

Prestartup times for custom nodes:
0.0 seconds: C:\ComfyUI\custom_nodes\rgthree-comfy
1.7 seconds: C:\ComfyUI\custom_nodes\ComfyUI-Manager

Checkpoint files will always be loaded safely.
Found comfy_kitchen backend eager: {'available': True, 'disabled': False, 'unavailable_reason': None, 'capabilities': ['apply_rope', 'apply_rope1', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'scaled_mm_nvfp4']}
Found comfy_kitchen backend cuda: {'available': False, 'disabled': True, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
Found comfy_kitchen backend triton: {'available': False, 'disabled': True, 'unavailable_reason': 'CUDA not available on this system', 'capabilities': []}
Total VRAM 25969 MB, total RAM 32305 MB
pytorch version: 2.11.0.dev20260202+xpu
Set vram state to: HIGH_VRAM
Device: xpu:0 Intel(R) Arc(TM) 140V GPU (16GB)
Using pytorch attention
Python version: 3.11.0 (main, Oct 24 2022, 18:26:48) [MSC v.1933 64 bit (AMD64)]
ComfyUI version: 0.12.2
Initializing frontend: Comfy-Org/ComfyUI_frontend@latest, requesting version details from GitHub...
[Prompt Server] web root: C:\ComfyUI\web_custom_versions\Comfy-Org_ComfyUI_frontend\1.39.6
ComfyUI-GGUF: Allowing full torch compile
### Loading: ComfyUI-Impact-Pack (V8.28.2)
[Impact Pack] Wildcard total size (0.00 MB) is within cache limit (50.00 MB). Using full cache mode.
[Impact Pack] Wildcards loading done.
### Loading: ComfyUI-Manager (V3.39.2)
[ComfyUI-Manager] network_mode: public
[ComfyUI-Manager] ComfyUI per-queue preview override detected (PR #11261). Manager's preview method feature is disabled. Use ComfyUI's --preview-method CLI option or 'Settings > Execution > Live preview method'.
### ComfyUI Version: v0.12.2-2-gef73070 | Released on '2026-02-04'
[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/custom-node-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json

Initializing ControlAltAI Nodes
Using pytorch attention
(RES4LYF) Init
(RES4LYF) Importing beta samplers.
(RES4LYF) Importing legacy samplers.

[rgthree-comfy] Loaded 48 epic nodes. 🎉

[rgthree-comfy] ComfyUI's new Node 2.0 rendering may be incompatible with some rgthree-comfy nodes and features, breaking some rendering as well as losing the ability to access a node's properties (a vital part of many nodes). It also appears to run MUCH more slowly spiking CPU usage and causing jankiness and unresponsiveness, especially with large workflows. Personally I am not planning to use the new Nodes 2.0 and, unfortunately, am not able to invest the time to investigate and overhaul rgthree-comfy where needed. If you have issues when Nodes 2.0 is enabled, I'd urge you to switch it off as well and join me in hoping ComfyUI is not planning to deprecate the existing, stable canvas rendering all together.

Import times for custom nodes:
0.0 seconds: C:\ComfyUI\custom_nodes\websocket_image_save.py
0.0 seconds: C:\ComfyUI\custom_nodes\comfyui_memory_cleanup
0.0 seconds: C:\ComfyUI\custom_nodes\metadata-extractor
0.0 seconds: C:\ComfyUI\custom_nodes\comfyui-simple-prompt-batcher
0.0 seconds: C:\ComfyUI\custom_nodes\images-grid-comfy-plugin
0.0 seconds: C:\ComfyUI\custom_nodes\derfuu_comfyui_moddednodes
0.0 seconds: C:\ComfyUI\custom_nodes\controlaltai-nodes
0.0 seconds: C:\ComfyUI\custom_nodes\ComfyMath
0.0 seconds: C:\ComfyUI\custom_nodes\comfyui-kjnodes
0.0 seconds: C:\ComfyUI\custom_nodes\gguf
0.0 seconds: C:\ComfyUI\custom_nodes\rgthree-comfy
0.1 seconds: C:\ComfyUI\custom_nodes\ComfyUI-GGUF
0.2 seconds: C:\ComfyUI\custom_nodes\ComfyUI-Manager
0.2 seconds: C:\ComfyUI\custom_nodes\ComfyUI-LTXVideo
0.4 seconds: C:\ComfyUI\custom_nodes\ComfyUI-Impact-Pack
0.7 seconds: C:\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
1.1 seconds: C:\ComfyUI\custom_nodes\RES4LYF

Context impl SQLiteImpl.
Will assume non-transactional DDL.
Assets scan(roots=['models']) completed in 0.055s (created=0, skipped_existing=200, orphans_pruned=0, total_seen=200)
Disabling intermediate node cache.
Starting server

To see the GUI go to: http://0.0.0.0:8188
FETCH ComfyRegistry Data: 5/123
FETCH ComfyRegistry Data: 10/123
FETCH ComfyRegistry Data: 15/123
FETCH ComfyRegistry Data: 20/123
FETCH ComfyRegistry Data: 25/123
FETCH ComfyRegistry Data: 30/123
FETCH ComfyRegistry Data: 35/123
FETCH ComfyRegistry Data: 40/123
FETCH ComfyRegistry Data: 45/123
FETCH ComfyRegistry Data: 50/123
FETCH ComfyRegistry Data: 55/123
FETCH ComfyRegistry Data: 60/123
FETCH ComfyRegistry Data: 65/123
FETCH ComfyRegistry Data: 70/123
FETCH ComfyRegistry Data: 75/123
FETCH ComfyRegistry Data: 80/123
FETCH ComfyRegistry Data: 85/123
FETCH ComfyRegistry Data: 90/123
FETCH ComfyRegistry Data: 95/123
FETCH ComfyRegistry Data: 100/123
got prompt
model weight dtype torch.bfloat16, manual cast: None
model_type FLOW
FETCH ComfyRegistry Data: 105/123
FETCH ComfyRegistry Data: 110/123
VRAM清理完成 [卸载模型: True, 清空缓存: True]
FETCH ComfyRegistry Data: 115/123
RAM清理完成 [37.5% → 33.3%, 释放: 1385MB]
VAE load device: xpu:0, offload device: xpu:0, dtype: torch.float16
FETCH ComfyRegistry Data: 120/123
Requested to load ACE15TEModel_
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.
loaded completely; 4673.04 MB loaded, full load: True
CLIP/text encoder model load device: xpu:0, offload device: xpu:0, current: xpu:0, dtype: torch.float16
Requested to load ACE15TEModel_
Requested to load ACEStep15
loaded completely; 4565.35 MB loaded, full load: True
100%|████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:08<00:00, 1.03s/it]
VRAM清理完成 [卸载模型: True, 清空缓存: True]
RAM清理完成 [35.2% → 28.7%, 释放: 2106MB]
Requested to load AudioOobleckVAE
loaded completely; 321.70 MB loaded, full load: True
Prompt executed in 149.05 seconds
Disabling intermediate node cache.
[ComfyUI-Manager] The ComfyRegistry cache update is still in progress, so an outdated cache is being used.
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] The ComfyRegistry cache update is still in progress, so an outdated cache is being used.
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
ComfyUI is up-to-date.
Updating: rgthree-comfy
[ComfyUI-Manager] Queued works are completed.
{'update-comfyui': 1, 'update-main': 16}

After restarting ComfyUI, please refresh the browser.
```

### Other

_No response_