this post was submitted on 09 Feb 2025
18 points (84.6% liked)

Linux

8877 readers
219 users here now

Welcome to c/linux!

Welcome to our thriving Linux community! Whether you're a seasoned Linux enthusiast or just starting your journey, we're excited to have you here. Explore, learn, and collaborate with like-minded individuals who share a passion for open-source software and the endless possibilities it offers. Together, let's dive into the world of Linux and embrace the power of freedom, customization, and innovation. Enjoy your stay and feel free to join the vibrant discussions that await you!

Rules:

  1. Stay on topic: Posts and discussions should be related to Linux, open source software, and related technologies.

  2. Be respectful: Treat fellow community members with respect and courtesy.

  3. Quality over quantity: Share informative and thought-provoking content.

  4. No spam or self-promotion: Avoid excessive self-promotion or spamming.

  5. No NSFW adult content

  6. Follow general lemmy guidelines.

founded 2 years ago
MODERATORS
 

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!

top 8 comments
sorted by: hot top controversial new old
[–] [email protected] 5 points 1 week ago* (last edited 1 week ago)

I've been using automatic1111 with models and Lora's from civtai.com I got quite good results.

E: making links links

[–] levzzz 4 points 1 week ago (1 children)

Try sd webui forge or comfyui. Most models you can find on civitai

[–] [email protected] 2 points 1 week ago* (last edited 1 week ago) (1 children)

sd webui forge

Does...it work with AMD? I see zero mentions for it on the page. All mentions are CUDA.

[–] levzzz 4 points 1 week ago

It should work out of the box, or there is a fork of it that does

[–] Blaster_M 4 points 1 week ago

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...

[–] Kentaree 3 points 1 week ago

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.

[–] just_another_person 1 points 1 week ago

Have a look on Hugging face and try some out. Filter to the open source ones and you'll find something.

[–] Pfeffy -2 points 1 week ago

If you can't Google, you probably can't use the software either.