Thanks for upkeeping these nodes, I'm sure there's a lot of requests and issues coming your way. I tried searching both repos to see if this was ever mentioned but did not find it.
For specific SD1.5 models I get the error:
Error occurred when executing Efficient Loader:
'l'
File "C:\StableDiffusion\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\StableDiffusion\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:\StableDiffusion\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\StableDiffusion\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 172, in efficientloader
encode_prompts(positive, negative, token_normalization, weight_interpretation, clip, clip_skip,
File "C:\StableDiffusion\ComfyUI\custom_nodes\efficiency-nodes-comfyui\efficiency_nodes.py", line 73, in encode_prompts
positive_encoded = bnk_adv_encode.AdvancedCLIPTextEncode().encode(clip, positive_prompt, token_normalization, weight_interpretation)[0]
File "C:\StableDiffusion\ComfyUI\custom_nodes\efficiency-nodes-comfyui\py\bnk_adv_encode.py", line 312, in encode
embeddings_final, pooled = advanced_encode(clip, text, token_normalization, weight_interpretation, w_max=1.0,
File "C:\StableDiffusion\ComfyUI\custom_nodes\efficiency-nodes-comfyui\py\bnk_adv_encode.py", line 262, in advanced_encode
return advanced_encode_from_tokens(tokenized['l'],
The two models I'm experiencing this with are Counterfeit by gsdf (rqdwdw on Civitai) and RealismEngine by razzzhf. Given this only seems to happen with specific checkpoints it leads me to believe this is either an issue with how those models were created or they're an edge use-case that the efficiency node does not like.
Extra details:
I'm pulling from a separate drive than where my instance of Comfy is installed.
I updated both Comfy and the efficiency nodes
I did a clean install of the efficiency nodes
Started a new workflow that only has the generator and sampler, same issue with the same checkpoints
Redownloaded the checkpoints and tried the different fp versions
Any insights would be much appreciated! I'm a designer first, technically minded second, so hope it's not something super obvious I'm doing on the user side.
Thanks for upkeeping these nodes, I'm sure there's a lot of requests and issues coming your way. I tried searching both repos to see if this was ever mentioned but did not find it.
For specific SD1.5 models I get the error:
The two models I'm experiencing this with are Counterfeit by gsdf (rqdwdw on Civitai) and RealismEngine by razzzhf. Given this only seems to happen with specific checkpoints it leads me to believe this is either an issue with how those models were created or they're an edge use-case that the efficiency node does not like.
Extra details:
Any insights would be much appreciated! I'm a designer first, technically minded second, so hope it's not something super obvious I'm doing on the user side.