list index out of range

[abjeet1]

Workflow used -workflow-ai-made-simple-lora-custom-flux-lora-zhI6ZH2Loc8A9Izk71Ej-seal_harmful_40-openart.ai.json

I am using A5000 24gb gpu

Error details -
Error occurred when executing XlabsSampler:

list index out of range

File "/home/ComfyUI/execution.py", line 316, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/home/ComfyUI/execution.py", line 191, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
File "/home/ComfyUI/execution.py", line 168, in _map_node_over_list
process_inputs(input_dict, i)
File "/home/ComfyUI/execution.py", line 157, in process_inputs
results.append(getattr(obj, func)(**inputs))
File "/home/ComfyUI/custom_nodes/x-flux-comfyui/nodes.py", line 411, in sampling
x = denoise(
File "/home/ComfyUI/custom_nodes/x-flux-comfyui/sampling.py", line 178, in denoise
t = timesteps[t_idx]

[OliverCrosby]

I fixed this by putting an empty latent into the Xlabs Sampler instead of a vae-encoded version of the loaded image. My input image was 1024x1024, encoded with the ae.safetensors vae, so I expected it to work.

Having to use an empty latent as input might not be ideal for every use case...

[AiTools9]

latent_image: latent input for flux, may be empty latent or encoded with FLUX AE (VAE Encode) image (for image-to-image using)

The error occurs if you have an image input while the latent image value is set to 0. You must increase the image to image strength in order for the Sampler to be able to use it.