What models/LoRA you use with SD?

It doesn’t really matter. He’s right - Midjourney is leagues ahead as far as actually following your prompt and having it be aesthetically pleasing. I say this as someone who has made several Dreambooth and fine tuned models and has started to use Stable Diffusion in my work.

Now, if you happen to find or make a SD model that’s exactly what you’re looking for you’re in luck. I have no interest in it but it seems like all of the anime models work pretty well.

You obviously have a ton more control in SD, especially now with ControlNet. But if you want to see the Ninja Turtles surfing on Titan in the style of Rembrandt or something Midjourney will probably kick out something pretty good. Stable Diffusion won’t.

I thought Midjourney was better as well, until I saw some recent videos from Corridor Crew on Youtube. For those who don't know, this is a VFX studio in LA that tries to keep at the cutting-edge of video production techniques and posts content to their Youtube channel, and they have a massive number of followers and several viral videos.

They recently created a full 7-minute anime using Stable Diffusion with their own models and their existing video production gear, I'll post the links and let the results speak for themselves

The actual 7-minute anime piece produced using SD: https://www.youtube.com/watch?v=GVT3WUa-48Y

Behind the scenes: "Did we change anime forever?" https://www.youtube.com/watch?v=_9LX9HSQkWo "VFX reveal before and after" https://www.youtube.com/watch?v=ljBSmQdL_Ow

While this is cool this doesn't change my opinion at all.

Each still image is still not that impressive. Good for them using the tech in a clever way but i don't find this that relevant.

those trees are part of a forest, you know.

the benefits of such fine grained control aren't a trick. it's why they were able to scrap together frames that don't jump all over the place (mostly).

the other benefit of such a broadly hacked upon model is that it grows in leaps and bounds.

All due respect to mid journey, but the stable diffusion hype is not just hype.

I agree, don't believe it's just hype, that level of control is useful, but for outright image quality and for most use cases, midjourney is better.

I still don't like the look of most of the Stable diffusion images, they just look slightly off/amateurish to me, where as midjourney produces images that make you go 'wow'

If you wanted to use these tools, midjourney would be my go too, with stable diffusion a backup for when some of the additional features were needed, perhaps inpanting on a midjourney image and using controlnet if needed but if you just want a pure image, midjourney is what you want.

No one uses raw stable diffusion though, there are model mixes for whatever usecase you have.

> but automatic1111 was always around and 'completely crushes any competitors' is rather rich

Controlnet is the big new thing, it is on a different level from earlier img2img.