[Template Bug]: image_hidream_o1_dev

### Confirmation

- [x] I have confirmed this is a workflow template mistake

### Template Name

image_hidream_o1_dev

### Problem Description

I have installed the models for image_hidream_o1_dev by downloading them by the link from the workflow, I instaleld them to the folders and added a normal image with the original prompt from the workflow and the generated image is grey, I did not even touch the settings.

No errors in the log .

### ComfyUI Mode

Legacy Mode

### Error Message / Logs

```text
got prompt
Found quantization metadata version 1
Detected mixed precision quantization
Using mixed precision operations
model weight dtype torch.bfloat16, manual cast: torch.bfloat16
model_type FLOW
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[MultiGPU Core Patching] text_encoder_device_patched returning device: cuda:0 (current_text_encoder_device=cuda:0)
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Found quantization metadata version 1
Detected mixed precision quantization
Using mixed precision operations
model weight dtype torch.bfloat16, manual cast: torch.bfloat16
model_type FLOW
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[MultiGPU Core Patching] text_encoder_device_patched returning device: cuda:0 (current_text_encoder_device=cuda:0)
CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load HiDreamO1TE
loaded completely; 13416.55 MB usable, 0.00 MB loaded, full load: True
loaded completely; 13416.55 MB usable, 0.00 MB loaded, full load: True
Requested to load HiDreamO1
Model HiDreamO1 prepared for dynamic VRAM loading. 7693MB Staged. 0 patches attached. Force pre-loaded 145 weights: 605 KB.
100%|████████████████████████████████████████████████████████████████| 28/28 [00:13<00:00, 2.03it/s]
Requested to load PixelspaceConversionVAE
loaded completely; 0.00 MB loade
```