SantiUsma
SantiUsma
Hi everyone. I had the same problem so I did something weird. The error said the "ddim_sigmas", "ddim_alphas", "ddim_alphas_prev", "ddim_sqrt_one_minus_alphas" are unexpected keys in the checkpoint so it is not...
And about your first_stage_models question, you could specify the autoencoder first_stage checkpoint path in the yaml config. In the model.params.first_stage_config you add a ckpt_path: "path_to_model.ckpt" Something like this: first_stage_config: target:...
> Yes! delet the " and 'cond_stage_model' not in params" in the " for i,params in enumerate(keys): " and try it again.
Hello, indeed the problem is in the shape. If they put in the variable shape=[3,64,64] the model runs normally, this variable indicates what should be the size of the latent...
Hi, to train a latent diffusion model with a personalized dataset you have to create the dataset Class. In the file ldm/data/ you will found the different dataset Class, I...
``` class Personalize0(Dataset): def __init__(self, txt_file, size=128, interpolation="bicubic", flip_p=0.5, is_mri=True, val=False ): self.data_paths = txt_file self.is_mri=is_mri self.image_paths=pd.read_csv(self.data_paths)["Image_path"] if is_mri: self.mri_paths=pd.read_csv(self.data_paths)["MRI_path"] if val: self.mri_paths=self.mri_paths[:1024] self.image_paths=self.image_paths[:1024] self.labels = { "relative_file_path_": [l for...
> Theoretically yes, if you are talking about the image size. But it is better if you retrain your autoencoder before training the LDM in this personalized size to have...
> @SantiUsma Thanks! can you explain what it's meaning in your code ` # default to score-sde preprocessing` in the getitem method? and what exactly I need to add in...
> > > @SantiUsma Thanks! can you explain what it's meaning in your code ` # default to score-sde preprocessing` in the getitem method? and what exactly I need to...
> > > > > @SantiUsma Thanks! can you explain what it's meaning in your code ` # default to score-sde preprocessing` in the getitem method? and what exactly I...