ValueError: You are trying to load the model files of the `variant=fp16`, but no such modeling files are available.

[lolo-VP]

Job config/examples/train_lora_sdxl_24gb_1.0.yaml failed with error: You are trying to load the model files of the variant=fp16, but no such modeling files are available.

Traceback (most recent call last):

File "/workspace/Lorakit/lorakit/.venv/lib/python3.11/site-packages/lorakit/cli/lorakit.py", line 31, in main
job.run()

File "/workspace/Lorakit/lorakit/.venv/lib/python3.11/site-packages/lorakit/train.py", line 896, in run
self._generate_samples(accelerator, global_step, vae, unet, text_encoder_1, text_encoder_2)

File "/workspace/Lorakit/lorakit/.venv/lib/python3.11/site-packages/lorakit/train.py", line 537, in _generate_samples
pipeline = StableDiffusionXLPipeline.from_pretrained(

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

File "/workspace/Lorakit/lorakit/.venv/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)

       ^^^^^^^^^^^^^^^^^^^

File "/workspace/Lorakit/lorakit/.venv/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py", line 891, in from_pretrained
raise ValueError(error_message)

ValueError: You are trying to load the model files of the variant=fp16, but no such modeling files are available.

(.venv) root@XXXXXXXXXXXX:/workspace/Lorakit/lorakit#

[lolo-VP]

That's what's causing the error because the stabilityai/stable-diffusion-xl-base-1.0 model doesn't have an fp16 branch on Hugging Face. Right?

I'll test it:

model:
name_or_path: "stabilityai/stable-diffusion-xl-base-1.0" # huggingface repo name or path to local folder
#variant: "fp16"