CODE Stable Diffusion: Step by Step (PyTorch, VAE, UNet, CLIP)
Stable Diffusion is a text-to-image latent diffusion model created by the researchers and engineers from CompVis, Stability AI and LAION. Licenses apply. Generative AI.
It's trained on 512x512 images from a subset of the LAION-5B database. This model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts. With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 10GB VRAM. AI Art. AI art tool.
All credits to:
https://huggingface.co/models?library...
https://huggingface.co/CompVis/stable...
Colab NB to follow along:
https://colab.research.google.com/git...
#ai
#stablediffusion
#naturallanguageprocessing
#text-to-image
#generativeai