open-pose-editor VS octoart

you can do it here or just use openpose module alone in controlnet with a given image

You can try this : https://zhuyu1997.github.io/open-pose-editor/

It won't need a processor unless you're using an input photograph that matches the composition you want. For the mlsd input, maybe try draw two horizontal white lines on a black canvas, for where you want the floor and ceiling meet the walls, and play with the strength. There's also tools like https://zhuyu1997.github.io/open-pose-editor/ and https://app.posemy.art/ and various extensions. I know you said "without resorting to creating a background"... just google some gym photographs?

You can also try looking at https://zhuyu1997.github.io/open-pose-editor/Web based (May also have a extension) but it does have fingers and will give you a Pose, Depth, Normal and canny image.

https://zhuyu1997.github.io/open-pose-editor/ set background image and make openpose matchstick man

Open Pose Editor is great but doesn't have better IK functionality of Magic Poser even though its hands and feet have IK. https://zhuyu1997.github.io/open-pose-editor/

Yeah that could also work, but some more complicated poses are tough :) I saw that this one are quite good: https://zhuyu1997.github.io/open-pose-editor/

Web version: https://zhuyu1997.github.io/open-pose-editor/ (Exports Canny/Depth/Normal/Edge model images to PNG for import).

I really liked the idea and went on to build OctoArt - generator of AI pictures in a GitHub logo style.

Hey there

Some time ago I built a site that generates AI pictures in a style of GitHub logo (https://octoart.vercel.app/). It's completely free, and even official GitHub accounts in Twitter and Instagram (yes turns out they have Instagram) posted about it. It was fun.

So I thought it would be cool to build an app that works with any logo, so people can generate nice branded pictures with their logo.

I went on to build https://logopictureai.com/. It's build with Next.js, Replicate API and Supabase.

It's a very early version, I built it in a weekend.

It works like this: your upload a logo, type a prompt (or select a predefined one), select number of variations to generate and click a button. Images will be delivered to your email in 2-3 minutes.

As I said, it's pretty early and I am not sure if it's really useful. It works decently with most logos, but sometimes can generate something weird.

Anyways, would love to hear your thought. Thanks!