scribble-diffusion VS stable-diffusion-webui-two-shot

Text to image with Scribble Diffusion

Eh, I don't think this is better than https://scribblediffusion.com/. None of the three images were at all like my drawing, but Scribble Diffusion did include the right elements in the right places.

Demo: Scribble Diffusion GitHub: Scribble Diffusion Repository

You can get several free acccess interactions with a version here ControlNet Scribble (ie if you keep using it for long enough/ several tries then it will ask you to set up an account) ...... this is the backend for a simpler browser interface at Scribble Diffusion but the ControlNet one above allows you to upload an image, so, yeah draw a scribble on a piece of paper, take a photo with your phone and then upload

I feel embarrassed to jump on the AI bandwagon, but have you tried uploading this into something like Scribble Diffusion?

ScribbleDiffusion: Turns scribbles with descriptions into really cool images.

scribblediffusion.com

Thanks so much! You should try it! In this case my drawing is more elaborate, but you will be surprised that the simplest drawing can achieve great results! If your drawing is not very good then the prompt is very important! Give it a try at https://scribblediffusion.com/ and let me know how it went!

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.