Well, not too shabby for Dall-E Mini, maybe Midjourney COULD put out something more detailed... but i'm skeptic about the faces.
Well i used Midjourney,and the exact same prompt yielded this result.
Dall-E Mini was more on point with what i had in mind.
Same prompt, Dall-E Mini and Midjourney.
I think Midjourney is stilystically more constrained and Dall-E mini is let to run wild on prompts, so it has more variety.
Same prompt, first two are Dall-E Mini and the others are Midjourney's
Midjourney's results are more pretty but Dalle's are more WILD.
Now had a chance to test an AI model running StableDiffusion and i gave it the same prompt. Dall-E mini is still winning to me.
@hideki AI is definitely coming along nicely, I wonder how long it will be until AI starts operating major infrastructure
@Mr_NutterButter Midjourney has nice outputs i think if you are willing to refine your first results a lot, but at the same time i think the results kind of same-y?.... ike Midjourney has a very marked style, i think the training model is powerful but the training pool is a bit limited... probably.
@hideki yoo is mik
The good thing is that you can run StableDiffusion however you'd like, and that you have lots of people doing the prompt engineering for you because of this.
StableDiffusion is, I think, the worst in needing looong prompts to get cool shit. But it's worth it.
"A portrait of a samurai, young with long hair, wearing white robe, brandishing katana with red hilt, matte painting, hyper realistic, very detailed, intricate, forest, unreal engine, dramatic cinematic lighting rendered by octane, 8 k, detailed"
Steps: 50, Sampler: k-diffusion, CFG scale: 7, Seed: 3866088339, GFPGAN
using everything as described in https://rentry.org/kretard
Same thing, exactly same prompt, and i prefer Dall-E results because they are more aligned to what i am looking for, despite being less detailed.