Fresh install of beta 280, can't load any LoRA models

[jnwebster]

I performed a clean install of https://github.com/rupeshs/fastsdcpu/releases/tag/v1.0.0-beta.280
I downloaded the Fantasy_Classes_SD.safetensors model from https://civitai.com/models/287148/fantasy-classes-sd
I confirmed the model type is LoRA and base model is SD 1.5
I copied the .safetensors file into the lora_models subdirectory
I launched fastsdcpu via ./start-webui.sh
I generated a small test image to initialize the pipeline
I navigated to the "Lora Models" tab on the webui
I see that "Fantasy_Classes_SD" is listed in the available models
I clicked the "Load selected LoRA" button
The console window reports the following errors:

Selected Lora Model :Fantasy_Classes_SD
Lora weight :0.5
LoRA adapter name : Fantasy_Classes_SD
Traceback (most recent call last):
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/loaders/peft.py", line 352, in load_lora_adapter
    incompatible_keys = set_peft_model_state_dict(self, state_dict, adapter_name, **peft_kwargs)
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/peft/utils/save_and_load.py", line 158, in set_peft_model_state_dict
    load_result = model.load_state_dict(peft_model_state_dict, strict=False)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/torch/nn/modules/module.py", line 2624, in load_state_dict
    raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel:
	size mismatch for down_blocks.0.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for down_blocks.0.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.0.attentions.0.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for down_blocks.0.attentions.0.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for down_blocks.0.attentions.1.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for down_blocks.0.attentions.1.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.0.attentions.1.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for down_blocks.0.attentions.1.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for down_blocks.1.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for down_blocks.1.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.1.attentions.0.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for down_blocks.1.attentions.0.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for down_blocks.1.attentions.1.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for down_blocks.1.attentions.1.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.1.attentions.1.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for down_blocks.1.attentions.1.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for down_blocks.2.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for down_blocks.2.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.2.attentions.0.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for down_blocks.2.attentions.0.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for down_blocks.2.attentions.1.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for down_blocks.2.attentions.1.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for down_blocks.2.attentions.1.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for down_blocks.2.attentions.1.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for up_blocks.1.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for up_blocks.1.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.1.attentions.0.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for up_blocks.1.attentions.0.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for up_blocks.1.attentions.1.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for up_blocks.1.attentions.1.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.1.attentions.1.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for up_blocks.1.attentions.1.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for up_blocks.1.attentions.2.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for up_blocks.1.attentions.2.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.1.attentions.2.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.1.attentions.2.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for up_blocks.1.attentions.2.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for up_blocks.2.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for up_blocks.2.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.2.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.2.attentions.0.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for up_blocks.2.attentions.0.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for up_blocks.2.attentions.1.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for up_blocks.2.attentions.1.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.2.attentions.1.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.2.attentions.1.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for up_blocks.2.attentions.1.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for up_blocks.2.attentions.2.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for up_blocks.2.attentions.2.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.2.attentions.2.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.2.attentions.2.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 640, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 640]).
	size mismatch for up_blocks.2.attentions.2.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([640, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([640, 32]).
	size mismatch for up_blocks.3.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for up_blocks.3.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.3.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.3.attentions.0.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for up_blocks.3.attentions.0.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for up_blocks.3.attentions.1.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for up_blocks.3.attentions.1.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.3.attentions.1.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.3.attentions.1.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for up_blocks.3.attentions.1.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for up_blocks.3.attentions.2.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for up_blocks.3.attentions.2.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.3.attentions.2.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for up_blocks.3.attentions.2.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
	size mismatch for up_blocks.3.attentions.2.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([320, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 32]).
	size mismatch for mid_block.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for mid_block.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).
	size mismatch for mid_block.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for mid_block.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 768]) from checkpoint, the shape in current model is torch.Size([32, 1024]).
	size mismatch for mid_block.attentions.0.proj_out.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 1280, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 1280]).
	size mismatch for mid_block.attentions.0.proj_out.lora_B.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([1280, 32, 1, 1]) from checkpoint, the shape in current model is torch.Size([1280, 32]).

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/gradio/queueing.py", line 624, in process_events
    response = await route_utils.call_process_api(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/gradio/route_utils.py", line 323, in call_process_api
    output = await app.get_blocks().process_api(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/gradio/blocks.py", line 2015, in process_api
    result = await self.call_function(
             ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/gradio/blocks.py", line 1562, in call_function
    prediction = await anyio.to_thread.run_sync(  # type: ignore
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/anyio/to_thread.py", line 61, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 2525, in run_sync_in_worker_thread
    return await future
           ^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 986, in run
    result = context.run(func, *args)
             ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/gradio/utils.py", line 865, in wrapper
    response = f(*args, **kwargs)
               ^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/src/frontend/webui/lora_models_ui.py", line 68, in on_click_load_lora
    load_lora_weight(
  File "/home/joel/fastsdcpu/src/backend/lora.py", line 69, in load_lora_weight
    pipeline.load_lora_weights(
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/loaders/lora_pipeline.py", line 202, in load_lora_weights
    self.load_lora_into_unet(
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/loaders/lora_pipeline.py", line 406, in load_lora_into_unet
    unet.load_lora_adapter(
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/loaders/peft.py", line 377, in load_lora_adapter
    module.delete_adapter(adapter_name)
    ^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1962, in __getattr__
    raise AttributeError(
AttributeError: 'Linear' object has no attribute 'delete_adapter'

[rupeshs]

It is working without any issues, ensure that you are using correect LCM lora as shown below

[jnwebster]

As I mentioned, this is a fresh install and so all of the models are the defaults

I noticed in your screenshot above that you have the LCM-LoRA mode selected.
When I select that mode instead of LCM, I still can't load the desired LoRA model, but when I attempt to generate an image I get the following error:

{'clip_skip': 1,
 'controlnet': None,
 'diffusion_task': 'text_to_image',
 'dirs': {'controlnet': '/home/joel/fastsdcpu/controlnet_models',
          'lora': '/home/joel/fastsdcpu/lora_models'},
 'gguf_model': {'clip_path': None,
                'diffusion_path': None,
                'gguf_models': '/home/joel/fastsdcpu/models/gguf',
                't5xxl_path': None,
                'vae_path': None},
 'guidance_scale': 1.0,
 'image_height': 512,
 'image_width': 512,
 'inference_steps': 1,
 'init_image': None,
 'lcm_lora': {'base_model_id': 'Lykon/dreamshaper-8',
              'lcm_lora_id': 'Fantasy_Classes_SD'},
 'lcm_model_id': 'stabilityai/sd-turbo',
 'lora': {'enabled': False,
          'fuse': False,
          'models_dir': '/home/joel/fastsdcpu/lora_models',
          'path': '/home/joel/fastsdcpu/lora_models/Fantasy_Classes_SD.safetensors',
          'weight': 0.5},
 'negative_prompt': '',
 'number_of_images': 1,
 'openvino_lcm_model_id': 'rupeshs/sd-turbo-openvino',
 'prompt': 'dragon\n',
 'rebuild_controlnet_pipeline': False,
 'rebuild_pipeline': False,
 'seed': 123123,
 'strength': 0.6,
 'token_merging': 0.0,
 'use_gguf_model': False,
 'use_lcm_lora': True,
 'use_offline_model': False,
 'use_openvino': False,
 'use_safety_checker': False,
 'use_seed': False,
 'use_tiny_auto_encoder': False}
***** Init LCM-LoRA pipeline - Lykon/dreamshaper-8 *****
Loading pipeline components...: 100%|█████████████| 7/7 [00:01<00:00,  5.92it/s]
Error in generating images: Fantasy_Classes_SD is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with `token` or log in with `huggingface-cli login`.
Traceback (most recent call last):
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/utils/_http.py", line 402, in hf_raise_for_status
    response.raise_for_status()
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/requests/models.py", line 1026, in raise_for_status
    raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/Fantasy_Classes_SD/resolve/main/pytorch_lora_weights.safetensors

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/utils/hub_utils.py", line 289, in _get_model_file
    model_file = hf_hub_download(
                 ^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1007, in hf_hub_download
    return _hf_hub_download_to_cache_dir(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1114, in _hf_hub_download_to_cache_dir
    _raise_on_head_call_error(head_call_error, force_download, local_files_only)
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1655, in _raise_on_head_call_error
    raise head_call_error
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1543, in _get_metadata_or_catch_error
    metadata = get_hf_file_metadata(
               ^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1460, in get_hf_file_metadata
    r = _request_wrapper(
        ^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 283, in _request_wrapper
    response = _request_wrapper(
               ^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 307, in _request_wrapper
    hf_raise_for_status(response)
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/utils/_http.py", line 452, in hf_raise_for_status
    raise _format(RepositoryNotFoundError, message, response) from e
huggingface_hub.errors.RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-694c0827-76fbabae6fb9a0a259fcc2b1;425212be-1390-46bd-a55f-d848ddcfe6fc)

Repository Not Found for url: https://huggingface.co/Fantasy_Classes_SD/resolve/main/pytorch_lora_weights.safetensors.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated. For more details, see https://huggingface.co/docs/huggingface_hub/authentication
Invalid username or password.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/joel/fastsdcpu/src/context.py", line 57, in generate_text_to_image
    self.lcm_text_to_image.init(
  File "/home/joel/fastsdcpu/src/backend/lcm_text_to_image.py", line 333, in init
    self.pipeline = get_lcm_lora_pipeline(
                    ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/src/backend/pipelines/lcm_lora.py", line 89, in get_lcm_lora_pipeline
    load_lcm_weights(
  File "/home/joel/fastsdcpu/src/backend/pipelines/lcm_lora.py", line 33, in load_lcm_weights
    pipeline.load_lora_weights(
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/loaders/lora_pipeline.py", line 196, in load_lora_weights
    state_dict, network_alphas = self.lora_state_dict(pretrained_model_name_or_path_or_dict, **kwargs)
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/loaders/lora_pipeline.py", line 300, in lora_state_dict
    state_dict = _fetch_state_dict(
                 ^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/loaders/lora_base.py", line 251, in _fetch_state_dict
    model_file = _get_model_file(
                 ^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/home/joel/fastsdcpu/env/lib/python3.11/site-packages/diffusers/utils/hub_utils.py", line 304, in _get_model_file
    raise EnvironmentError(
OSError: Fantasy_Classes_SD is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with `token` or log in with `huggingface-cli login`.

I did not get this LoRA model from huggingface, I got itfrom civitai. Do I need to get my LoRA models from huggingface only?

[rupeshs]

No, LoRA models can be downloaded from civitai and place it inside lora folder fastsd will load it at the startup.
Please checkout this tutorial https://www.youtube.com/watch?v=N_LUxd6G2nk

[jnwebster]

I watched the video provided and got the same result.
Here are the steps I followed:

1. I created a brand new VM running a fresh install of Debian 13.2
2. I installed Python and uv (python version 3.13.5)
3. I downloaded beta 280 of fastsdcpu and ran the install script
4. I downloaded the exact same LoRA model in your youtube video above, CuteCartoon15V-LiberteRedmodModel-Cartoon-CuteCartoonAF.safetensors and placed the .safetensors file in the lora_models folder
5. I started fastsdcpu via start-webui.sh
6. I initialized the pipeline with a sample image
7. I attempted to load the CuteCartoon15V-LiberteRedmodModel-Cartoon-CuteCartoonAF LoRA model and got the same error in my message above

I followed your instructional video step for step and it's still not working, can't load the selected LoRA model with the same error
RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel

[rupeshs]

@jnwebster I have tested this on a fresh Debian 13.2 it is working as expected please see the screenshot.
Mode - LCM-LoRA
Model - Lykon/dreamshaper8
Lora - CuteCartoon15V-LiberteRedmodModel
I would suggest to do a fresh clone of fastsdcpu in another new folder ,install and check it should work.( Don't use your existing installation)

[jnwebster]

Did you need to do anything specific with your installed version of python or anything like that?
I'm not sure what I'm doing wrong that it's not working for me.

Here is what happens when I make a fresh install:

Starting FastSD CPU env installation...
Found python command
Python version : 3.13.5
Using CPython 3.11.6
Creating virtual environment at: env
Activate with: source env/bin/activate
Using Python 3.11.6 environment at: env
Resolved 12 packages in 520ms
Installed 12 packages in 266ms
 + filelock==3.20.0
 + fsspec==2025.12.0
 + jinja2==3.1.6
 + markupsafe==2.1.5
 + mpmath==1.3.0
 + networkx==3.6.1
 + numpy==2.3.5
 + pillow==12.0.0
 + sympy==1.14.0
 + torch==2.8.0+cpu
 + torchvision==0.23.0+cpu
 + typing-extensions==4.15.0
Using Python 3.11.6 environment at: env
Resolved 130 packages in 222ms
Prepared 3 packages in 31ms
Uninstalled 3 packages in 8ms
Installed 121 packages in 731ms
 + absl-py==2.3.1
 + accelerate==1.6.0
 + aiofiles==23.2.1
 + aiohappyeyeballs==2.6.1
 + aiohttp==3.13.2
 + aiosignal==1.4.0
 + annotated-doc==0.0.4
 + annotated-types==0.7.0
 + antlr4-python3-runtime==4.9.3
 + anyio==4.12.0
 + attrs==25.4.0
 + certifi==2025.11.12
 + cffi==2.0.0
 + charset-normalizer==3.4.4
 + click==8.3.1
 + coloredlogs==15.0.1
 + contourpy==1.3.3
 + controlnet-aux==0.0.7
 + cycler==0.12.1
 + datasets==2.14.4
 + diffusers==0.33.0
 + dill==0.3.7
 + einops==0.8.1
 + fastapi==0.128.0
 + fastapi-mcp==0.3.0
 + ffmpy==1.0.0
 + flatbuffers==25.12.19
 + fonttools==4.61.1
 + frozenlist==1.8.0
 + gradio==5.6.0
 + gradio-client==1.4.3
 + h11==0.16.0
 + hf-xet==1.2.0
 + httpcore==1.0.9
 + httpx==0.28.1
 + httpx-sse==0.4.3
 + huggingface-hub==0.36.0
 + humanfriendly==10.0
 + idna==3.11
 + imageio==2.37.2
 + importlib-metadata==8.7.1
 + jax==0.7.1
 + jaxlib==0.7.1
 + kiwisolver==1.4.9
 + lazy-loader==0.4
 + markdown-it-py==4.0.0
 + matplotlib==3.10.8
 + mcp==1.6.0
 + mdurl==0.1.2
 + mediapipe==0.10.21
 + ml-dtypes==0.5.4
 + multidict==6.7.0
 + multiprocess==0.70.15
 - numpy==2.3.5
 + numpy==1.26.4
 + omegaconf==2.3.0
 + onnx==1.16.0
 + onnxruntime==1.17.3
 + opencv-contrib-python==4.11.0.86
 + opencv-python==4.8.1.78
 + openvino==2025.1.0
 + openvino-telemetry==2025.2.0
 + opt-einsum==3.4.0
 + optimum==1.27.0
 + optimum-intel==1.23.0
 + orjson==3.11.5
 + packaging==25.0
 + pandas==2.3.3
 + peft==0.6.1
 - pillow==12.0.0
 + pillow==9.4.0
 + propcache==0.4.1
 + protobuf==4.25.8
 + psutil==7.2.0
 + pyarrow==22.0.0
 + pycparser==2.23
 + pydantic==2.9.2
 + pydantic-core==2.23.4
 + pydantic-settings==2.8.1
 + pydub==0.25.1
 + pygments==2.19.2
 + pyparsing==3.3.1
 + pyqt5==5.15.11
 + pyqt5-qt5==5.15.18
 + pyqt5-sip==12.17.2
 + python-dateutil==2.9.0.post0
 + python-dotenv==1.2.1
 + python-multipart==0.0.12
 + pytz==2025.2
 + pyyaml==6.0.1
 + regex==2025.11.3
 + requests==2.32.5
 + rich==14.2.0
 + ruff==0.14.10
 + safehttpx==0.1.7
 + safetensors==0.7.0
 + scikit-image==0.24.0
 + scipy==1.16.3
 + semantic-version==2.10.0
 + sentencepiece==0.2.1
 + setuptools==80.9.0
 + shellingham==1.5.4
 + six==1.17.0
 + sounddevice==0.5.3
 + sse-starlette==3.1.1
 + starlette==0.50.0
 + tifffile==2025.12.20
 + timm==1.0.22
 + tokenizers==0.21.4
 + tomesd==0.1.3
 + tomli==2.3.0
 + tomlkit==0.12.0
 + tqdm==4.67.1
 + transformers==4.48.0
 + typer==0.21.0
 - typing-extensions==4.15.0
 + typing-extensions==4.10.0
 + tzdata==2025.3
 + urllib3==2.6.2
 + uvicorn==0.40.0
 + websockets==12.0
 + xxhash==3.6.0
 + yarl==1.22.0
 + zipp==3.23.0
FastSD CPU installation completed,press any key to continue...

And here is what happens when I run start-webui.sh

Starting FastSD CPU please wait...
Found python command
Python version : 3.13.5
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/torch/onnx/_internal/registration.py:162: OnnxExporterWarning: Symbolic function 'aten::scaled_dot_product_attention' already registered for opset 14. Replacing the existing function with new function. This is unexpected. Please report it on https://github.com/pytorch/pytorch/issues.
  warnings.warn(
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/openvino/runtime/__init__.py:10: DeprecationWarning: The `openvino.runtime` module is deprecated and will be removed in the 2026.0 release. Please replace `openvino.runtime` with `openvino`.
  warnings.warn(
FastSD CPU -  v1.0.0 beta 280
Running on Linux platform
OS: Linux-6.12.57+deb13-amd64-x86_64-with-glibc2.41
Processor: 
Using device : cpu
Output path : /home/joel/fastsdcpu/results
Found 6 LCM models in config/lcm-models.txt
Found 7 stable diffusion models in config/stable-diffusion-models.txt
Found 4 LCM-LoRA models in config/lcm-lora-models.txt
Found 10 OpenVINO LCM models in config/openvino-lcm-models.txt
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_5m_224 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_5m_224. This is because the name being registered conflicts with an existing name. Please check if this is not expected.
  return register_model(fn_wrapper)
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_11m_224 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_11m_224. This is because the name being registered conflicts with an existing name. Please check if this is not expected.
  return register_model(fn_wrapper)
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_21m_224 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_21m_224. This is because the name being registered conflicts with an existing name. Please check if this is not expected.
  return register_model(fn_wrapper)
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_21m_384 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_21m_384. This is because the name being registered conflicts with an existing name. Please check if this is not expected.
  return register_model(fn_wrapper)
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/controlnet_aux/segment_anything/modeling/tiny_vit_sam.py:654: UserWarning: Overwriting tiny_vit_21m_512 in registry with controlnet_aux.segment_anything.modeling.tiny_vit_sam.tiny_vit_21m_512. This is because the name being registered conflicts with an existing name. Please check if this is not expected.
  return register_model(fn_wrapper)
Starting web UI mode
No lora models found, please add lora models to /home/joel/fastsdcpu/lora_models directory
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/gradio/components/dropdown.py:226: UserWarning: The value passed into gr.Dropdown() is not in the list of choices. Please update the list of choices to include:  or set allow_custom_value=True.
  warnings.warn(
/home/joel/fastsdcpu/env/lib/python3.11/site-packages/gradio/components/base.py:194: UserWarning: show_label has no effect when container is False.
  warnings.warn("show_label has no effect when container is False.")
* Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.

Note that it says "No lora models found, please add lora models to /home/joel/fastsdcpu/lora_models directory" but the .safetensors file is in the folder:

Any thoughts? Is this a permissions issue? Do I need to run fastsdcpu in a different location or with admin privileges?

[rupeshs]

Yes.try to run using root user it should detect the lora models

[jnwebster]

I elevated my command prompt to be acting as the root user (su and not sudo) and ran ./start-webui.sh
The program started just like normal.
I initialized the pipeline with a sample image, and I noticed that the program downloaded several extra files it hadn't downloaded before on first run.

• model_index.json
• scheduler_config.json
• tokenizer_config.json
• special_tokens_map.json
• config.json
• merges.txt
• vocab.json
• vae/diffusion_pytorch_model.safetensors
• unet/diffusion_pytorch_model.safetensors
• text_encoder/model.safetensors

This made me hopeful that things would be different this time, so I attempted to load the LoRA model and got the same error result as before.
I thought maybe it needed to shut down and start again, so I stopped the program and started it again, still as root, and I got the same error result.

With this knowledge that things are different when running as root, I attempted another thing:
I tried clearing my install and redownloading a fresh clone and running install.sh as root in addition to running start-webui.sh as root
I was hopeful that performing all actions as root would help, I noted that the files listed above did not get loaded on first run, so I'm guessing they were included in the installation.
Unfortunately I recieved the same errors as before.
It still indicated that it couldn't find any LoRA models in the lora_models folder despite one being there and threw all of the errors above when I tried to load it.
I'm not sure what you did to get it to work that I'm missing. I've tried to lay out what I'm doing step by step so hopefully you can steer me in the right direction, but nothing I'm changing is doing anything to make it work.

Latest python 3.13.5, latest uv, latest fastsdcpu running as root - same errors as above.
What am I missing that I can't get it to succeed but you can't get it to fail?

[monstruosoft]

It should be possible to run FastSD as a normal, non-root, user. Can you list the permissions on the files in the lora_models folder?. Do you get the same error when running the CLI or Qt GUI versions?.

[jnwebster]

Same process as before:

• created new debian 13.2 vm
• installed python 3 & uv
• cloned & installed fastsdcpu

All files & folders belong to my user who ran the install script, and that user has read/write permissions on all files & folders:

I have attempted to run the qt desktop ui but debian 13.2 runs gnome and installing qt5 doesn't seem to do the right thing.

To run the CLI, I attempted to follow the instructions located here: https://github.com/rupeshs/fastsdcpu?tab=readme-ov-file#linux-users
Which resulted in a permission denied error

[monstruosoft]

Try with python src/app.py -i.
As for the Qt version, I've seen that error before. In my case, I guess it required the installation of libxcb from the Linux package manager. You could also try setting the environment variable QT_QPA_PLATFORM=wayland as suggested in your screenshot.

[jnwebster]

Thank you for the handy tip for running the CLI version, that did the trick
Running the CLI version, here are my actions:

1. Option 1, Text to Image to initialize the pipeline
2. Option 7, Edit LoRA settings
3. Option 2, Load new LoRA model
4. Input lora_models/CuteCartoon15V-LiberteRedmodModel-Cartoon-CuteCartoonAF.safetensors
5. Input the default lora weights

The application crashed with the same error as above that starts with RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel:

Thank you for the handy tip for running the QT version, that did the trick
Running the QT version, here are my actions:

1. Generate a sample image to initialize the pipeline
2. On the LoRA Models tab, selec the CuteCartoon15V-LiberteRedmodModel-Cartoon-CuteCartoonAF model and hit "Load selected LoRA"

The application crashed with the same error as above that starts with RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel:

[rupeshs]

@jnwebster The error you got is

""RuntimeError: Error(s) in loading state_dict for UNet2DConditionModel:
	size mismatch for down_blocks.0.attentions.0.proj_in.lora_A.Fantasy_Classes_SD.weight: copying a param with shape torch.Size([32, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([32, 320]).
size mismatch for down_blocks.0.attentions.0.proj_in.lora_B.Fantasy_Classes_SD.weight: copying a param with shape "

Root cause of the error is you are loading a LoRA/adapter checkpoint or mismatched UNet weights as if they were a full UNet2DConditionModel, causing the state_dict load to fail. In simple words mismatched model and LoRA,trying to load sd1.5 base model with SDXL LoRA model is an example.

Possible causes

• Using incompatible models

Resolution

• Double check the configuration, mode
• Try to install it on another machine

If possible you can screenrecord and share your work flow with models and settings and the error state

[jnwebster]

Please review the default settings here: #351 (comment)

Below is my screen recording from creating a new VM to experiencing the error.
Please ignore my struggles with getting my user added to sudo, I've only done it a thousand times before - when you get to 7:00 skip ahead to 10:35.
The sample image pipeline initialization completes at 15:20
Screen recording