New error while running on Colab since today

Linaqruf / kohya-trainer

Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning

Apache License 2.0

1.82k stars 296 forks source link

New error while running on Colab since today #332

Closed DreamCloudWalker closed 5 months ago

DreamCloudWalker commented 6 months ago

mean ar error (without repeats): 0.006993006993007034 prepare accelerator

ValueError: fp16 mixed precision requires a GPU

CalledProcessError: Command '['/usr/bin/python3', 'train_network.py', '--sample_prompts=/content/LoRA/config/sample_prompt.txt', '--dataset_config=/content/LoRA/config/dataset_config.toml', '--config_file=/content/LoRA/config/config_file.toml']' returned non-zero exit status 1.

asahi0416 commented 5 months ago

I also encountered the same error. Could you please tell me the solution?

DreamCloudWalker commented 5 months ago

My fault, the real reason is this error : load Diffusers pretrained models model is not found as a file or in Hugging Face, perhaps file name is wrong? My default safetensors download failed, after I change the safetensors link, it works fine!