WASasquatch
commented
1 year ago It works fine for SDXL, you just can't mix model types since your conditioning it only for one. So like you can't hookup refiner as secondary_model since the conditioning input is from base model. Have thought about updating that but I think without adding 6 to 8 conditionings (for the additive prompts too) it may be better to have text inputs and clip and secondary_clip
Not sure. Will need to look into it more.
This is more of a question than anything else.
!!! Exception during processing !!! Traceback (most recent call last): File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "C:\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "C:\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\WAS_Node_Suite.py", line 8630, in sample positive = comb.addWeighted(pos_additive, positive, pos_strength)[0] File "C:\ComfyUI_windows_portable\ComfyUI\nodes.py", line 97, in addWeighted tw = torch.mul(t1, conditioning_to_strength) + torch.mul(t0, (1.0 - conditioning_to_strength)) RuntimeError: The size of tensor a (1280) must match the size of tensor b (2048) at non-singleton dimension 2
Getting this error when running the KSampler (cycle) with SDXL. This indicates that an SD1.5 model or resource is being used within this node. Is there some way you could release an updated version of this node which does not contain whatever feature that can't be used with SDXL models?
I would very much like to try including this version of the sampler in my workflows, but am finding it impossible without redownloading SD1.5 models I got rid of a month ago.