stable-diffusion-webui-composable-lora VS paint-with-words-sd

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.

I think it works with Regional Prompting in combination with and Composable LoRA (both std. Auto1111-extensions). Never tried myself, though.

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Latent Couple and Composable Lora don't work on Vlad Automatic (something to do with those extensions beind made for a outdated version of A1111 webUI).

Composable LoRA Enables using AND keyword(composable diffusion) to limit LoRAs to subprompts. Useful when paired with Latent Couple extension.

Its https://github.com/opparco/stable-diffusion-webui-composable-lora

I tried using composable lora but it is hardcoded to look for the "and", plus it has certain issues that haven't been resolved..

Only one good suggestion can be had here and that is the composable lora extension. I think you need to use it together with the latent couple extension.

Oh this is super easy, just grab the Latent Couple extension and the Composable LoRA extension. Using this you can define multiple sections for different characters, then you can have a prompt/lora unique to each section/character.

I am refering to this btw: https://github.com/cloneofsimo/paint-with-words-sd

This essentially supercharges the Nvidia eDiffi / SD paint-with-words attempts done for the same thing previously.

There is stable diffusion paint with words GitHub which probably does exactly this, but no UI ever: https://github.com/cloneofsimo/paint-with-words-sd

personally i want to see the ediffi paint w/words stable diffusion extension https://github.com/cloneofsimo/paint-with-words-sd/commit/789419e3a34f43a1454df5a940020cfa531fbc63 that clonesofimo was working on before he stopped

Just found there is a repo for an NVIDIA eDiff-I style img2img workflow for Stable Diffusion. For those unfamiliar, this lets you specify where parts of your text prompt should be placed in the image giving you much greater control on the composition e.g.

Paint-with-Words might eventually allow something along those lines, but it's a bit awkward to use now, and AFAIK you still get bleedthrough between multiple human subjects.

someone attempted something like paint with words but I think Nvidia's version is better looking.