search

gligen / GLIGEN

Open-Set Grounded Text-to-Image Generation
MIT License
1.91k stars 145 forks source link

Train using Stability AI's stable diffusion 2.1 #75

Open nityanandmathur opened 4 months ago

nityanandmathur commented 4 months ago

Hello! Since, GLIGEN is trained on CompVis/SD-1.4, could you please let me know how it can be trained using Stability AI's stable diffusion?

TonyLianLong commented 2 months ago

I just built a codebase called IGLIGEN that I use to train GLIGEN on SDv1.5/2.1. It also supports ModelScope (text-to-video generation). It is trained with SA-1B dataset which is only ~300GB after preprocessing and has 11M images. It is more "modern" (i.e., it is based on diffusers training script) and supports flash attention. The dataset, preprocessing script, and training script are included in the repo. Feel free to contact me for suggestions for this repo.

Repo: https://github.com/TonyLianLong/igligen