Incredible preservation of detail between frames... It's unlike any AI animation I've ever seen. Honestly I would love to know more about the workflow to achieve such stunning movements... The bodies, the water, the steam, the clothes, and the shading are so insanely consistent compared to older animations. I'm dying to know more about how this was done.
Incredible preservation of detail between frames... It's unlike any AI animation I've ever seen. Honestly I would love to know more about the workflow to achieve such stunning movements... The bodies, the water, the steam, the clothes, and the shading are so insanely consistent compared to older animations. I'm dying to know more about how this was done.
Pre-trained Stable Diffusion weights, also known as checkpoint files, are models designed for generating images of a general or specific genre. What images a model can generate depends on the data used to train them.
Okey, I think the image reached perfection here. Thank you both asanajm, drfisura, Touhou was one of my favorite franchise, and I do love to see Reimu like this.
Hi, IMO, the nipple looks fine, it just looks like an inverted nipple, which only about 10-20% of people have inverted nipples, which makes them rather rare to see, but I do like this new edit the areola looks better and the nipple looks ready to pop out.
Your little Aina is going places! You should be happy!
Maybe they're not a fan of explicit content featuring their characters, idk. I've always felt the same way about mine, but I'd take any art I get regardless (I guess)
So there was a comment originally or was it later added? I thought it was more the eyes being slightly different and remnants of the orange lines. Sigh, well, the vagina's been reworked multiple times, so I guess I still wasn't able to perfect it enough
"The whole image looks smudged" is something I don't really agree with, it's a stylistic effect with blues and yellows being lighting/shading but I'll try to learn from my mistakes
It really is. I have to give myself a little credit for understanding all the settings a lot better (I was using way too high a CFG Scale and number of samples which was blowing out the contrast), but the much better models compared to NovelAI and AOM are really doing the heavy lifting here in terms of detail.
I used to love lot AOM, but now it feels a little rusty, the first time I used SD Colab it was overwhelming, there are so many options and a lot more control, sadly since Colab died I don't feel like using AI anymore, but I'm glad people can enjoy this. Keep it up.
Wow, this is a complete upgrade from 8 months before, love how this AI technology is moving forward so fast.
It really is. I have to give myself a little credit for understanding all the settings a lot better (I was using way too high a CFG Scale and number of samples which was blowing out the contrast), but the much better models compared to NovelAI and AOM are really doing the heavy lifting here in terms of detail.
