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..
catbox preserves the exif data with most of the info.
Nice. Yeah, it's a pain. I see "Model hash: dd8147b45d, Model: 0.7(absolutereality_v16) + 0.3(uberRealisticPornMerge_urpmv13)", is that done by using the Checkpoint Merger?
I saw the elf that was just posted and thought I'd try something new 🙃 Let me know how you like her as an elf stripper.
After playing more with the prompt, it definitely helps that they are standing next to each other and that there's little overlap, that's when bad anatomy happens a lot.
Dunno, I used a 2.1 model and the images just came out like this. I threw away something like 80% though, for various reasons (bad anatomy, bad eyes and missing variety).
Lol, yeah. It took a few tries to get the prompt right so that they don't all wear red tank tops.
Thanks so much!
Yeah, some invalid JSON thing
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.