jimgoo.ai

I'm Jimmie Goode and specialize in the development and deployment of generative AI, with a focus on Large Language Models and stable diffusion text2image models.

MidJourney-style image progress using SDXL, Diffusers, WebSockets, React, and FastAPI.

As the MidJourney Discord bot is generating images for your prompt over some number of diffusion steps, it makes the wait time a little more enjoyable by showing you your images at the current step. I was surprised that there wasn't any paid API or simple code on GitHub that had this feature, given that it's the best text2image user experience I've seen, so I built the frontend and backend using SDXL, Diffusers, WebSockets, React, and FastAPI and made the code open source.

Reconstructing the Mind’s Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors

This is a paper I wrote with Stability AI MedARC that uses contrastive learning and diffusion priors to essentially read minds. It decodes the image that a person is viewing while in an fMRI machine using only the measured brain activity and sets a new state-of-the-art result for this task. Accepted as a spotlight for the NeurIPS 2023 conference. This was a great experience with open science and really highlighted to me the power of this format.

View All Articles

Stay up to date

Get notified when I publish something new, and unsubscribe at any time.

Work

  1. Company
    Trase Systems
    Role
    Staff Machine Learning Engineer
    Date
  2. Company
    Choose Your Horizon
    Role
    CTO
    Date
  3. Company
    SparkCognition
    Role
    Staff Data Scientist
    Date
  4. Company
    DeUmbra
    Role
    Research Scientist
    Date