Hi guys! I’ve tried quite a few months back Fooocus for AI image generation, and while it kinda worked well, it tended to have trouble figuring more than one person on the drawing (ie, man and woman dancing my end up with any combination of men/men, woman/woman, or just a random group dance etc). Moreover, I just found out that this project is just in maintenance mode.
So…What’s the cool software for AI generation/Stable diffusion etc? Preferably AMD compatible, as I have a 7800XT.
Thanks!
I’ve been using automatic1111 with models and Lora’s from civtai.com I got quite good results.
E: making links links
If you can’t Google, you probably can’t use the software either.
As for models… depending on what style you are looking for… nonrealistic / toon style, Pony Diffusion (v6 currently), with lots of loras and tunes for different subjects or themes. Also bïfrost and variants for photorealism…
I have the same card as you and I’ve had some success with ComfyUI. It can be very complex if you want to do advanced stuff but there are a lot of preexisting workflows that will do most of the common scenarios.
Try sd webui forge or comfyui. Most models you can find on civitai
sd webui forge
Does…it work with AMD? I see zero mentions for it on the page. All mentions are CUDA.
It should work out of the box, or there is a fork of it that does
Have a look on Hugging face and try some out. Filter to the open source ones and you’ll find something.
