dpo-sdxl-text2image-v1
Direct Preference Optimization (DPO) for text-to-image diffusion models is a method to align diffusion models to text human preferences by directly optimizing on human comparison data.
text → image · made by mhdang
Sold by
Nobody in the catalogue publishes a price for this yet.
About
dpo-sdxl-text2image-v1 — an images model from mhdang.
It takes text and returns images. It was published in December 2023. The catalogue files it under image. Its weights are published under the openrail++ licence, which attaches conditions the plain open licences do not.
Every current figure
- Maker
- mhdang
- Register
- model
- Takes
- text
- Returns
- image
- Published
- December 2023
- Parameters
- 2.6 billion · read from its own weights
- Licence
- openrail++
Known as 1 name
mhdang/dpo-sdxl-text2image-v1