lovis93

/

Flux-2-Multi-Angles-LoRA-v2

like 95

No, I can confirm.

I tried it with diffusers & this is my tracestack of the error:

    pipeline.load_lora_weights(
  File "/usr/local/lib/python3.12/dist-packages/diffusers/loaders/lora_pipeline.py", line 5713, in load_lora_weights
    state_dict, metadata = self.lora_state_dict(pretrained_model_name_or_path_or_dict, **kwargs)
                           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/diffusers/loaders/lora_pipeline.py", line 5682, in lora_state_dict
    state_dict = _convert_non_diffusers_flux2_lora_to_diffusers(state_dict)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.12/dist-packages/diffusers/loaders/lora_conversion_utils.py", line 2435, in _convert_non_diffusers_flux2_lora_to_diffusers
    raise ValueError(f"`original_state_dict` should be empty at this point but has {original_state_dict.keys()=}.")
ValueError: `original_state_dict` should be empty at this point but has original_state_dict.keys()=dict_keys(['guidance_in.in_layer.lora_A.weight', 'guidance_in.in_layer.lora_B.weight', 'guidance_in.out_layer.lora_A.weight', 'guidance_in.out_layer.lora_B.weight']).