Error in loading Civit AI Lora: LCMTurboMix_Euler_A_fix #11062
Description
Describe the bug
This CIVITAI Lora has over 20k downloads and doesn't work with SDXL Pipeline. It is giving lora_unet_down_blocks_0_downsamplers_0_conv.alpha not supported error. I have uploaded the model on hugging face. Error appears on load_lora_weights() function
Reproduction
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0")
pipe.load_lora_weights("RhaegarKhan/LCMTurboMix_Euler_A_fix")
prompt = "<lora:LCMTurboMix2fix:1>,abstract portrait of 1girl,undefined gender,fragmented visual style,red and black color palette,evokes feelings of rebellion,passion,and freedom,blurred boundaries,high resolution,aesthetic,"
image = pipe(prompt).images[0]
Logs
Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:02<00:00, 3.35it/s]
LCMTurboMix_Euler_A_fix.safetensors: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████| 13.0M/13.0M [00:00<00:00, 38.8MB/s]
Traceback (most recent call last):
File "/home/user/runware/Ali/sd-base-api/lora.py", line 4, in <module>
pipe.load_lora_weights("RhaegarKhan/LCMTurboMix_Euler_A_fix")
File "/home/user/runware/shehzad/temp/sd-base-api/diffusers/src/diffusers/loaders/lora_pipeline.py", line 545, in load_lora_weights
state_dict, network_alphas = self.lora_state_dict(
^^^^^^^^^^^^^^^^^^^^^
File "/home/user/anaconda3/envs/3.7/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/home/user/runware/shehzad/temp/sd-base-api/diffusers/src/diffusers/loaders/lora_pipeline.py", line 695, in lora_state_dict
state_dict = _maybe_map_sgm_blocks_to_diffusers(state_dict, unet_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/user/runware/shehzad/temp/sd-base-api/diffusers/src/diffusers/loaders/lora_conversion_utils.py", line 59, in _maybe_map_sgm_blocks_to_diffusers
raise ValueError(f"Checkpoint not supported because layer {layer} not supported.")
ValueError: Checkpoint not supported because layer lora_unet_down_blocks_0_downsamplers_0_conv.alpha not supported.System Info
Diffusers version: Version: 0.33.0.dev0
Python: 3.12.9