|
|
--- |
|
|
language: en |
|
|
tags: |
|
|
- glid-3-xl |
|
|
- latent-diffusion |
|
|
|
|
|
license: mit |
|
|
--- |
|
|
|
|
|
|
|
|
erlich is the text2image latent diffusion model from CompVis (with additions from `glid-3-xl`) finetuned on a dataset collected from LAION-5B named Large Logo Dataset. It consists of roughly 100K images of logos with captions generated via BLIP using aggressive re-ranking. |
|
|
|
|
|
Replicate versions: |
|
|
[original](https://replicate.com/laion-ai/erlich/versions/36ad98eccc1965ea471c39b61e58f32d599b59dbf3c8dff9d701d4e9c77d8db3) |
|
|
[latest](https://replicate.com/laion-ai/erlich/versions/d146f48156973f404ec492e57103ac377cac1d2d2a8ead80152cd4a50ab444d6) |
