stable-diffusion-webui-two-shot VS prompt-fusion-extension

They do, it just needs more work. Stable Diffusion + Latent Couple + Composable LoRA let's you have an Elon model and a Mark model in different parts of the image. No Elon/Mark-ness dominating all the subjects.

https://github.com/opparco/stable-diffusion-webui-two-shothttps://github.com/butaixianran/Stable-Diffusion-Webui-Civitai-Helper https://github.com/opparco/stable-diffusion-webui-composable-lora https://github.com/thomasasfk/sd-webui-aspect-ratio-helper

Possibly with something like the Latent Couple extension + Composable LoRA, cf this video.

Would love to see "two shot" (https://github.com/opparco/stable-diffusion-webui-two-shot) implemented into the ui into the future, so far your ui is very satisfying and easy to use. Keep up the good work!

https://github.com/opparco/stable-diffusion-webui-two-shot/issues/54 found the solution, works for me right now.

So i noticed that Latent Couple and Composable Lora don't work on Vlad Automatic (something to do with those extensions beind made for a outdated version of A1111 webUI).

I try to use this and works ok, I just didn't try it much yet, prompting is became confusing for me. you can try it out and tell me what to do. area wight and general prompt got me confuse, sometimes work sometimes didn't, it's feels like we can just do two subject. idk

This is a tool for the Latent couple extension and I was asking about the Regional Prompter extension. I will give this one a try too.

Sounds like the Latent Couple extension: https://github.com/opparco/stable-diffusion-webui-two-shot.git

The real "deniability" of copying will come when the NLP community gets off of its collective rear end and implements actual prompt engineering (i.e. any technique I mention in here: https://gist.github.com/Hellisotherpeople/45c619ee22aac6865c...). Using "prompt blending" (i.e. https://github.com/ljleb/prompt-fusion-extension) will give genuine "deniability" on the grounds that "A beautiful story by {stephen_king|plato|aristotle|virgina_wolf}" will be very unique and moreover such kinds of interpolation are for the most part how real human writers write.

There are a bunch of extensions in the Automatic1111 eco-system which can be used for doing this sort of analysis, or related types of analysis.

One of my favorites is this: https://github.com/ljleb/prompt-fusion-extension

https://github.com/ljleb/prompt-fusion-extension https://github.com/DominikDoom/a1111-sd-webui-tagcomplete https://github.com/adieyal/sd-dynamic-prompts https://github.com/yfszzx/stable-diffusion-webui-images-browser

Link to extension : https://github.com/ljleb/prompt-fusion-extension

You can also use prompt fusion to interpolate in between 2 or more prompts. This opens up slightly more surgical steering possibilities, for example instead of writing [Keanu Reeves:Emma Watson:0.4] You could write [Keanu Reeves:Emma Watson:0.3,0.5].

Forget merging and try using prompt interpolation

jokes apart, this extention is so powerful