controlnet-moritzef/model_lr1e4

These are controlnet weights trained on stabilityai/stable-diffusion-2-1-base with new type of conditioning. You can find some example images below.

prompt: A realistic google streetview image taken in Berlin (Germany), that looks normal and has a beauty-score of 24, where scores are between 10 and 40 and higher scores indicate more beauty. prompt: A realistic google streetview image taken in New York (USA), that looks normal and has a beauty-score of 27, where scores are between 10 and 40 and higher scores indicate more beauty. prompt: A realistic google streetview image taken in Rome (Italy), that looks normal and has a beauty-score of 23, where scores are between 10 and 40 and higher scores indicate more beauty. prompt: A realistic google streetview image taken in Mexico City (Mexico), that looks very ugly and has a beauty-score of 18, where scores are between 10 and 40 and higher scores indicate more beauty. prompt: A realistic google streetview image taken in Tel Aviv (Israel), that looks normal and has a beauty-score of 24, where scores are between 10 and 40 and higher scores indicate more beauty. prompt: A realistic google streetview image taken in Kyoto (Japan), that looks very ugly and has a beauty-score of 16, where scores are between 10 and 40 and higher scores indicate more beauty. prompt: A realistic google streetview image taken in Gaborone (Botswana), that looks normal and has a beauty-score of 24, where scores are between 10 and 40 and higher scores indicate more beauty. prompt: A realistic google streetview image taken in Melbourne (Australia), that looks normal and has a beauty-score of 28, where scores are between 10 and 40 and higher scores indicate more beauty.

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]