Meet jp-Irena: My Latest Effort in Mastering Textural Inversion
I'm excited to introduce jp-Irena, a culmination of my ongoing journey in textural inversion. This model represents a unique blend of art and technology, honed through 5000 steps on the Stable Diffusion 1.5 model.
Training Data:
Developed using 14 original photographs I took, designed to inspire but not replicate exact likenesses.
Progressive learning rate: 0.05:10, 0.02:20, 0.01:60, 0.005:200, 0.002:500, 0.001:3000, 0.0005.
Detailed textural representation with 10 vectors per token.
Batch size of 1 and 1 gradient accumulation step.
I'm eager to see the unique and creative ways you'll use jp-Irena. Your interpretations, creations, and feedback are not just welcomed, but they are essential for the growth and evolution of this project. Share your creations and let's explore the possibilities of AI-driven art together!
Description
FAQ
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.