Suraj Patil Profile picture
Open Source @huggingface 🤗, nlp, diffusion, text2image
Oct 18, 2022 11 tweets 5 min read
#Dreambooth is a method to teach new concepts to #stablediffusion , we have a super simple script to train dreambooth in 🧨diffusers. But our users reported that the results weren't as good as other Compvis forks. So we dug deep and found out some cool tricks.
A 🧵 Training the text encoder along with the unet gives the best results in terms of image-text alignment and prompt composition.

Left image - frozen text encoder
Right Image - finetuned text encoder

The results are drastically improved :🤯 ImageImage
Sep 28, 2022 4 tweets 3 min read
dreambooth #stablediffusion training is now available in 🧨diffusers!

And guess what! You can run this on a 16GB colab in less than 15 mins!

Github: github.com/huggingface/di…
Colab for training: bit.ly/3SGPYmk
Colab for inference: bit.ly/3UJ4oUL You can also find (and share your own!) trained concepts trained with dreambooth in our Collaborative Concepts Library: hf.co/sd-dreambooth-…