LoRA Fine-tuning Error

[nanaj96]

ValueError: The provided pretrained_model_name_or_path "./pretrained_models/dit_model" is neither a valid local path nor a valid repo id. Please check the parameter.

[erwold]

--pretrained_model_path should point to the directory where you downloaded the F-Lite checkpoint locally. The directory should look roughly like this:
dit_model/, model_index.json, test_image.png, text_encoder/, tokenizer/, vae/

[nanaj96]

now i'm trying on the runpod server

[nanaj96]

you mean we need to download the models first server in the directory

[erwold]

Yes, you should download the model weights from huggingface and put them into the dit_finetuned folder