About the AutoEncoder - Githubissues

gligen / GLIGEN

Open-Set Grounded Text-to-Image Generation

MIT License

1.91k stars 145 forks source link

Open russellllaputa opened 12 months ago

russellllaputa commented 12 months ago

Dear authors,

Thank you for your excellent work, which inspires me a lot.

I'm wondering why you choose AutoEnocderKL instead of VQ model. Would using VQ-model makes any difference?