From 1b7bee142fe1932ca41af84e401eefd53eae0782 Mon Sep 17 00:00:00 2001 From: hardmaru Date: Wed, 7 Dec 2022 16:43:35 +0900 Subject: [PATCH] Update README.md --- README.md | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index a65e423..8ac3cc5 100644 --- a/README.md +++ b/README.md @@ -8,12 +8,17 @@ new checkpoints. The following list provides an overview of all currently availa ## News -**December 7, 2022** *(Version 2.1)* +**December 7, 2022** + +*Version 2.1* - New stable diffusion model (_Stable Diffusion 2.1-v_) at 768x768 resolution and (_Stable Diffusion 2.1-base_) at 512x512 resolution, both based on the same number of parameters and architecture as 2.0. - New models fine-tuned on 2.0, on a less restrictive NSFW filtering of the [LAION-5B](https://laion.ai/blog/laion-5b/) dataset, after reflecting on, and examining the assumptions made in 2.0, and consulting with the author of [LAION-5B](https://openreview.net/forum?id=M3Y74vmsMcY). -**November 24, 2022** *(Version 2.0)* +**November 24, 2022** + +*Version 2.0* + - New stable diffusion model (_Stable Diffusion 2.0-v_) at 768x768 resolution. Same number of parameters in the U-Net as 1.5, but uses [OpenCLIP-ViT/H](https://github.com/mlfoundations/open_clip) as the text encoder and is trained from scratch. _SD 2.0-v_ is a so-called [v-prediction](https://arxiv.org/abs/2202.00512) model. - The above model is finetuned from _SD 2.0-base_, which was trained as a standard noise-prediction model on 512x512 images and is also made available. - Added a [x4 upscaling latent text-guided diffusion model](#image-upscaling-with-stable-diffusion).