DeciDiffusion 2.0 is a 732 million parameter text-to-image latent diffusion model, generated with the help of AutoNAC, Deci’s proprietary Neural Architecture Search technology. Advanced training techniques were used to speed up training, improve training performance, and achieve better inference quality.
Model Card: huggingface.co/Deci/DeciDiffusion-v2-0
Colab Notebook: …google.com/…/11ui_krtk2dklhlrw0aa11midciw4dtub
HuggingFace Space: huggingface.co/spaces/deci/decidiffusion-v2-0
tagginator@utter.online [bot] 8 months ago
New Lemmy Post: Introducing DeciDiffusion 2.0: Text-to-Image Generation Optimized for Cost-Effective Hardware (https://lemmy.dbzer0.com/post/12590333)
Tagging: #StableDiffusion
(Replying in the OP of this thread (NOT THIS BOT!) will appear as a comment in the lemmy discussion.)
I am a FOSS bot. Check my README: https://github.com/db0/lemmy-tagginator/blob/main/README.md