I tried SD once and it was pretty good. It was a bit difficult, of course. Now I want to try image generation again. Do you still think I should use SD or a different tool?
For people who want something older that’s well documented: SDXL
For people who want the new fancy thing: Flux (vram hungry with 16fp dev, but you can go 8p or you can use the schnell variant, which just means “fast”)
For people who want the faster image generation: SDXL lightning.
For tools, people are split on using either python/huggingface, the automatic1111 webui or comfy UI, which is my personal favourite.
The hottest model now is flux, and the community is gravitating toward it after the failure of stable diffusion 3.
Tooling around it is still nascent and it is very demanding (12GB+ VRAM GPU highly recommended) so you could also start with Stable Diffusion XL, fairly mature at this point.
Removed by mod
Thx. Looks like there’s also ComfyUI. How about that?
If you’re using Mac, DiffusionBee is super easy to install and use, also supports FLUX
Removed by mod
It’s a front end for stable diffusion. It works well, so does automatic1111
you should ask that question on [email protected]
Flux is a Stable Diffusion killer and it might succeed it being that.
Better hands, better text, better composition. Not perfect either.
Flux is great is you have the RAM to run it locally: