Awesome

<a href="https://colab.research.google.com/gist/JohannesAck/2c4561a8a4d1522f752b1a86f3e24c12/multiscaleblendeddiffusioncolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a> <a href="https://replicate.com/arielreplicate/multi-stage-blended-diffusion"><img src="https://replicate.com/arielreplicate/multi-stage-blended-diffusion/badge"></a>

High-Resolution Image Editing via Multi-Stage Blended Diffusion

This repository includes our implementation of Multi-Stage Blended Diffusion, as described in our paper High-Resolution Image Editing via Multi-Stage Blended Diffusion

Our implementation builds on the original implementation of Latent Diffusion, available at (https://github.com/CompVis/latent-diffusion), which is licensed under the MIT license. Specifically multi-scale-blended-diffusion/ldm, multi-scale-blended-diffusion/configs, and multi-scale-blended-diffusion/models are entirely from latent diffusion.

Setup:

• Install the environment specified in multi-scale-blended-diffusion/environment.yaml:

conda env create -f environment.yaml

• Download the stable diffusion v1.4 from the huggingface space and copy it to multi-scale-blended-diffusion/models/ldm/stable-diffusion-v1/model.ckpt. This requires login and has to be done manually.
• Also download RealESRGANx4plus from here and place it in multi-scale-blended-diffusion/RealESRGAN_x4plus.pth:

wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth -P multi-scale-blended-diffusion/

Usage

To try our approach for interactive editing, use the multi-scale-blended-diffusion/InteractiveEditing.ipynb notebook locally, or use our colab demo.

To run, validate our approach on the examples used in our paper, use multi-scale-blended-diffusion/multi_scale_blended_diffusion.py.