MultiDiffusion VS stable-diffusion-webui-two-shot

For composing this approach works pretty well

https://multidiffusion.github.io/

So I've continued to experiment with how many papers I can fit into a single pipe and have them play nicely together. The images below were created by combining the panorama code from omerbt/MultiDiffusion with the ideas from albarji/mixture-of-diffusers. Also turns out nateraw/stable-diffusion-videos can be seen as a special case of a panorama (in latent space rather than prompt space).

Essentially, I fine-tuned Stable Diffusion 2.1 base (the 512x512) model on the ESA Hubble Deep Space Images & Captions dataset I collected from public Hubble images & captions. After around 33,000 training steps, I saved the model and was really impressed by the results. But I really wanted to be able to generate wallpaper-level quality space images, so I stumbled upon MultiDiffusion: a new project for generating massive panorama images using stable diffusion models. I then used hubble-diffusion-2 along with MultiDiffusion to generate each one of these amazing 2560x1536 images. Each image took a little over an hour to generate on a Google Colab T4 GPU. I used the following prompts for each of these images:

If you need generated and not upscaled 4k for some reason, try something like https://github.com/omerbt/MultiDiffusion

Project: https://multidiffusion.github.io/ Paper: https://arxiv.org/abs/2302.08113 GitHub: https://github.com/omerbt/MultiDiffusion

Quick Read: https://www.marktechpost.com/2023/02/24/meet-multidiffusion-a-unified-ai-framework-that-enables-versatile-and-controllable-image-generation-using-a-pre-trained-text-to-image-diffusion-model/ Paper: https://arxiv.org/abs/2302.08113 Github: https://github.com/omerbt/MultiDiffusion Project: https://multidiffusion.github.io/

So I haven't made many images with Stable Diffusion despite using it heavily. The reason is I've been messing with the internals of the diffusion pipe, to interfere with the diffusion process in different ways. Todays fun result is based on omerbt/MultiDiffusion for making panoramas.

If we combine Mixture of Diffusers + MultiDiffusion+ Composer+ cross-domain-compositing and probably some more I'm not thinking of.

I tried Regional Prompter and Latent Couple (https://github.com/ashen-sensored/stable-diffusion-webui-two-shot) extension but they don't seem to work properly (latter has awful documentation/examples).

Option 5 is to buy a smallish GPU farm and simply rely on good specific and regional prompting pushed through brute forced generations to extract similar looking places out of the thousands of hallucinations. Some loras, checkpoints, regional prompting with the Latent Couple extension in A1111, and an abundant abuse of ControlNet could also help.

Use Latent Couple with Composable LoRA instead

The solution to this is to use the 'Latent Couple' plugin.

All three used the same prompt, which requires the Latent Couple extension.

git clone -b feature/mask_selection https://github.com/ashen-sensored/stable-diffusion-webui-two-shot.git

There are some extensions that break things even when they're disabled. If you're using Latent Couple (two shot), uninstall / delete the folder and and use this fork: https://github.com/ashen-sensored/stable-diffusion-webui-two-shot

I used the Latent Couple extension with the following mask:

I was thinking about this extension.