qwen_image error mat1 and mat2 shapes cannot be multiplied

### 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

workflow:

### Actual Behavior

### Steps to Reproduce

work flow json:
{
"3": {
"inputs": {
"seed": 388600705609480,
"steps": 4,
"cfg": 1,
"sampler_name": "euler",
"scheduler": "beta",
"denoise": 1,
"model": [
"86",
0],
"positive": [
"6",
0],
"negative": [
"7",
0],
"latent_image": [
"58",
0]
},
"class_type": "KSampler",
"_meta": {
"title": "KSampler"
}
},
"6": {
"inputs": {
"text": "",
"clip": [
"67",
1]
},
"class_type": "CLIPTextEncode",
"_meta": {
"title": "$prompt.text"
}
},
"7": {
"inputs": {
"text": "NSFW",
"clip": [
"67",
1]
},
"class_type": "CLIPTextEncode",
"_meta": {
"title": "CLIP Text Encode (Negative Prompt)"
}
},
"8": {
"inputs": {
"samples": [
"3",
0],
"vae": [
"39",
0]
},
"class_type": "VAEDecode",
"_meta": {
"title": "VAE Decode"
}
},
"37": {
"inputs": {
"unet_name": "qwen_image_fp8_e4m3fn.safetensors",
"weight_dtype": "default"
},
"class_type": "UNETLoader",
"_meta": {
"title": "Load Diffusion Model"
}
},
"38": {
"inputs": {
"clip_name": "qwen_2.5_vl_7b_fp8_scaled.safetensors",
"type": "qwen_image",
"device": "default"
},
"class_type": "CLIPLoader",
"_meta": {
"title": "Load CLIP"
}
},
"39": {
"inputs": {
"vae_name": "qwen_image_vae.safetensors"
},
"class_type": "VAELoader",
"_meta": {
"title": "Load VAE"
}
},
"58": {
"inputs": {
"width": [
"90",
0],
"height": [
"91",
0],
"batch_size": 1
},
"class_type": "EmptySD3LatentImage",
"_meta": {
"title": "EmptySD3LatentImage"
}
},
"60": {
"inputs": {
"filename_prefix": "ComfyUI",
"images": [
"8",
0]
},
"class_type": "SaveImage",
"_meta": {
"title": "Save Image"
}
},
"67": {
"inputs": {
"lora_name": "Qwen-Image-Lightning-4steps-V1.0.safetensors",
"strength_model": 1,
"strength_clip": 1,
"model": [
"37",
0],
"clip": [
"38",
0]
},
"class_type": "LoraLoader",
"_meta": {
"title": "Load LoRA"
}
},
"86": {
"inputs": {
"shift": 3.1,
"model": [
"67",
0]
},
"class_type": "ModelSamplingAuraFlow",
"_meta": {
"title": "ModelSamplingAuraFlow"
}
},
"90": {
"inputs": {
"value": 768
},
"class_type": "easy int",
"_meta": {
"title": "$width.value"
}
},
"91": {
"inputs": {
"value": 1024
},
"class_type": "easy int",
"_meta": {
"title": "$height.value"
}
}
}

### Debug Logs

```powershell
Unloaded partially: 874.18 MB freed, 12753.34 MB remains loaded, 125.02 MB buffer reserved, lowvram patches: 0
loaded completely; 8341.67 MB usable, 7910.28 MB loaded, full load: True
Unloaded partially: 813.32 MB freed, 7096.96 MB remains loaded, 85.75 MB buffer reserved, lowvram patches: 0
loaded completely; 14117.59 MB usable, 13626.34 MB loaded, full load: True
0%| | 0/4 [00:00