Hi, I'm Jimmie, and this is my irregularly updated corner of the internet.

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

I've been working on helping ketamine therapy patients illustrate their experiences using stable diffusion. As the MidJourney Discord bot is generating images, 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, so I built the frontend and backend using SDXL, Diffusers, WebSockets, React, and FastAPI and made the code open source.

Setting a new SOTA on fMRI-to-Image at NeurIPS 2023

My journey into open research with Stability AI MedARC, where people were shown images while in an fMRI machine and we were able to decode those images using contrastive learning and diffusion models. So basically mind reading. We set a new state-of-the-art and got accepted as a spotlight for the NeurIPS 2023 conference. I had a good time being the oldest person in the Discord channels.

Training multi-concept DreamBooth stable diffusion models

Over the past few months I've trained several DreamBooth models for clients to inject new concepts into various base stable diffusion models. In each case, the client wanted to insert several new concepts into the model, as opposed to the typical case of inserting a single concept like a new face. In this post, I'll describe the process I used to train these models and the heuristics I've developed for hyperparameters.

View All Posts

Work

  1. Company
    Trase Systems
    Role
    Head of AI
    Date
  2. Company
    Choose Your Horizon
    Role
    CTO
    Date
  3. Company
    SparkCognition
    Role
    Staff Data Scientist
    Date
  4. Company
    DeUmbra
    Role
    Research Scientist
    Date