Spaces:

multimodalart

/

dreambooth-training

like 488

Running

I always get this error after the Freezing the text_encoder ... step when running locally on windows.

train_dreambooth.py", line 745, in run_training
    model_pred = unet(noisy_latents, timesteps, encoder_hidden_states).sample
RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.cuda.FloatTensor) should be the same