Open ahnjy7168 opened 2 months ago
Exactly the same issue with almost the same setup (using show text instead of cr text list to string) Prompt executed in 0.00 seconds got prompt [rgthree] Using rgthree's optimized recursive execution. !!! Exception during processing!!! list index out of range Traceback (most recent call last): File "C:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 141, in recursive_execute input_data_all = get_input_data(inputs, class_def, unique_id, outputs, prompt, extra_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\AI\ComfyUI_windows_portable\ComfyUI\execution.py", line 26, in get_input_data obj = outputs[input_unique_id][output_index]
IndexError: list index out of range
I even tried simplifying it as much as possible (and tried all models)
Same issue here
Had the same issure, on my end it was caused by only having one image in the folder.
In the "LoRA Capiton Load" node there is a condition that is triggered when only one image is present where I think they forgot to add some parameters in the returning statement.
if len(images) == 1:
return (images[0], 1)
elif len(images) > 1:
image1 = images[0]
for image2 in images[1:]:
if image1.shape[1:] != image2.shape[1:]:
image2 = comfy.utils.common_upscale(image2.movedim(-1, 1), image1.shape[2], image1.shape[1], "bilinear", "center").movedim(1, -1)
image1 = torch.cat((image1, image2), dim=0)
return text, path, image1, len(images)
As you can see if only one image is present the return statement returns only 2 parameters instead of 4. I've solved the issue by replacing return (images[0], 1)
with return (text, path, images[0], 1)
in the "LoRAcaption.py" file.
You can also circumvent the issue by placing more than one image in the folder.
onnxruntime==1.17.3
how do i solve this?