It seems like sh.itjust.works was down and this post didn't federate. Just trying to see what happens when I add a comment.
Edit: Yes, that seems to have done it.
I was just playing around with some mayhem prompts and insectoid aliens and it seems like bad anatomy can be a good thing for them. It's obviously not great and would need some more fine tuning. But this two headed fella isn't bad either.
What fun things can be done with bad anatomy?
Same prompt (post image) on sdxl:
Face palm seed in comments.
The defiant artist
After the machines had taken over every work of art had to be in the style the machines approved of. This defiant artist will be deported for reeducation and just learned that her family will be joining her.
Path to glory
Elite machine totenkopf troops on their way to eliminate the last human army.
That should be part of the interpretation ;-) Tbh, I don't really like that a lot of the suggestions here want a specific visual style, that radically reduces the artistic freedom, which I wanted to maximize with my suggestion.
At the opera
That looks more... like a dinosaur.. pretty cool!
Papers please
Yeah, kind of interesting how this came out, I mixed Ferrari with Colani.
Oh well, it doesn't really have the right logos, but I still think it's a nice picture.
I did add an artist for the image above, Gerald Brom. That definitely makes it more interesting visually. The problem is that the 1.5 models I have seem to be trained with them, but they don't really understand the prompt well, this is the best I got.
The 2.1 model I used does a good interpretation of the prompt, but apparently wasn't trained with different styles. It's probably built for photo realism. So I tried a different 2.1 model and got this, which seems to go in the right direction.
Lol, I should get back to work.
Thanks! You're right about the prompt, your image doesn't really match it but is much more appealing visually. My image above was made with SD2.1, I can get nicer looking stuff with 1.5 models, but then I have to be much more specific with the prompt. Hopefully SDXL will improve all of that.
I made a batch of 10 and this is the only image that actually put a lemming into beans..
I tried.. but couldn't get anything as good as yours in stable diffusion. This is the best..
It looks like midjourney is automatically adding context to the prompt? That crowd certainly looks good. Time for SDXL..
..a lemmynaut is starting to feel uneasy. She has seen that classic movie.
Made with the help of https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111 , not sure why it's named like that tbh, it has a multi regional prompt thing which helped to separate background and lemmynaut.
Lol, yeah. It took a few tries to get the prompt right so that they don't all wear red tank tops.
For some reason I can't add more images to the post body, I'll try in the comments below. Here are links:
I'm still new to stable diffusion and learning. Today I combined the visual styles of different artists for the first time, I already had the spaceship prompt and added an artist, and then I added a styled person in the foreground. Which, somewhat surprisingly, gave me a good image super fast. This is fun.
It has been a few hectic weeks, but now the CEO is taking their well deserved vacation while the engineers put out any fires.
I guess something was lost with sdxl, no face palm any more.