0%

AI Painting

1. What

Stable Diffusion is a state of the art text-to-image model that generates images from text.

Online test by Hugging Face

E.g the text: a samoyed running on the moon

image-20221022210437827

Confusion:

  1. How text to image
  2. What kind of ML/DL tech used

2. How

Ref By Vox

5 step:

  1. Prepare training data
  2. Deep learning
  3. Latent space
  4. Generation (diffusion)
  5. Output

The key step is the latent space and diffusion

  • The deep learning network would learn from the dataset to learn all kinds of latent space for different word. For example, how yellow is the image, how round is the object, etc.

  • Diffusion start with noise and invert the noise step, guess the true data from noisy data Ref

image-20221022211653230

From Gaussin to inverse the bayesian. the label would work as a guide as the distribution