• [x] Accel logistics
• [x] readmission form!!
• [x] testing accuracy for logistic regression
• [x] K Means math & implementation
• [x] stable diffusion hack
  • [ ] try writing → image

web app with a colab backend: https://anvil.works/learn/tutorials/google-colab-to-web-app

build your own diffuser on colab (last section of the notebook): https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/stable_diffusion.ipynb#scrollTo=0SXnxd-ZrSfy

MVP for image extraction

• [x] return the sentence the prompt is based on
• [ ] study type of styles user can input
• [ ] try more examples with sentence and prompt extract
• prompt engineer
  • truncate part of the sentence that doesn’t have nouns
  • style
  • trending 4k / definition
  • avoid people?
• maybe we can offer both object extract and sentence itself? And maybe 2 objects instead of just 1?

P1:

• generate number of images based on blog length