Add Latent Diffusion Model to generate Brain images conditioned on text embeddings

[Warvito]

Add a version of our brain image generator, that is conditioned on text sentences instead on float vectors (containing age, gender, and brain volumes).

With this approach, it will be easier to users to download the model and fine-tune it into their own list of condioning variables (the current version limits the user to use other things instead the original conditionings) (Related to #293).