From afb2ab1d2ee476c04d8df2b7d730e240df82a072 Mon Sep 17 00:00:00 2001 From: David Bielejeski <2463282+djbielejeski@users.noreply.github.com> Date: Wed, 28 Sep 2022 15:21:01 -0500 Subject: [PATCH] Moving hugging face diffusers lower. --- README.md | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/README.md b/README.md index 8f3585e..0163530 100644 --- a/README.md +++ b/README.md @@ -9,21 +9,13 @@ - [They don't look like you at all!](#they-dont-look-like-you) - [They sorta look like you, but exactly like your training images](#they-sorta-look-like-you-but-exactly-like-your-training-images) - [They look like you, but not when you try different styles](#they-look-like-you-but-not-when-you-try-different-styles) +- [Hugging Face Diffusers](#hugging-face-diffusers) - [Original Readme From Xavier Xiao](#original-readme-from-xavierxiao) # "Dreambooth" on Stable Diffusion ![image](https://user-images.githubusercontent.com/100188076/192390551-cb89364f-af57-4aed-8f3d-f9eb9b61cf95.png) -# Hugging Face Diffusers - Alternate Option - -Note: This is a diffuser implementation, and use is much more complicated than using a *.ckpy file. - -Dreambooth is now supported in Hugging Face diffusers for training with stable diffusion, try it out in the colab: - -[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb) - - ## Notes by Joe Penna ### **INTRODUCTIONS!** Hi! My name is Joe Penna. @@ -183,8 +175,19 @@ No problem. We can fix that with the prompt: `JoePenna person in a portrait photograph, JoePenna person in a 85mm medium format photo of JoePenna person` + ### More tips and help here: [Stable Diffusion Dreambooth Discord](https://discord.com/channels/1023277529424986162/1024716296610385981) +# Hugging Face Diffusers - Alternate Option + +Note: This is a diffuser implementation, and use is much more complicated than using a *.ckpy file. + +Dreambooth is now supported in Hugging Face diffusers for training with stable diffusion, try it out in the colab: + +[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/sd_dreambooth_training.ipynb) + + + # Original Readme from XavierXiao This is an implementtaion of Google's [Dreambooth](https://arxiv.org/abs/2208.12242) with [Stable Diffusion](https://github.com/CompVis/stable-diffusion). The original Dreambooth is based on [Imagen](https://imagen.research.google/) text-to-image model. However, neither the model nor the pre-trained weights of Imagen is available. To enable people to fine-tune a text-to-image model with a few examples, I implemented the idea of Dreambooth on Stable diffusion.