From 4e409af95c66f4ec27315360a7b1911a6641912d Mon Sep 17 00:00:00 2001 From: hardmaru Date: Fri, 24 Mar 2023 15:07:06 +0900 Subject: [PATCH] Update UNCLIP.MD --- doc/UNCLIP.MD | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/doc/UNCLIP.MD b/doc/UNCLIP.MD index bc4c3b2..fc2fc2a 100644 --- a/doc/UNCLIP.MD +++ b/doc/UNCLIP.MD @@ -5,14 +5,16 @@ trained to invert CLIP image embeddings. We finetuned SD 2.1 to accept a CLIP ViT-L/14 image embedding in addition to the text encodings. This means that the model can be used to produce image variations, but can also be combined with a text-to-image embedding prior to yield a full text-to-image model at 768x768 resolution. + +If you would like to try a demo of this model on the web, please visit https://clipdrop.co/stable-diffusion-reimagine + We provide two models, trained on OpenAI CLIP-L and OpenCLIP-H image embeddings, respectively, available from [https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip](https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip/tree/main). -To use them, download from Hugging Face, and put and the weights into the `checkpoints` folder. +To use them, download from Hugging Face, and put and the weights into the `checkpoints` folder. + #### Image Variations ![image-variations-l-1](../assets/stable-samples/stable-unclip/unclip-variations.png) -If you would like to try a demo of this model, please visit https://clipdrop.co/stable-diffusion-reimagine - Run ```