Nice. Really catches the brisk and creepy autumn night that's appropriate for Halloween. Can just about hear those bats squealing and feel a chilly breeze.
Left eye look weird, but it looks a bit like ahegao so it's fine I think.
On another note, @木呗雲鸟 if you've generated the images yourself, it'd be great if you could tag them as self_upload and you can add an artist tag for yourself. Links to loras could be placed in the commentary too (thanks for sharing the links btw, I wish more people did it for the less known loras).
Bottom of the horns are messed up as if there's extra piece of skin, and the teeth are inconsistent as well. I am generally not a fan of these animated ones since I've barely seen any that actually look good to my eye. It's all up to a preference of course, but hopefully you understand at least some of the downvotes now.
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.
Nice check. Deleted this one because of a minor detail and approved this one: post #46919 and this one: post #33303 and this one too... post #38489 Cringe...
And to add to the comment above, you can also flag low quality posts to put them back in the queue for the regular 3-day check.
Nice check. Deleted this one because of a minor detail and approved this one: post #46919 and this one: post #33303 and this one too... post #38489 Cringe...
none of the posts you mentioned were approved, those posts did not go through the approval queue when they were uploaded. also, if you have a disagreement you can appeal for a second chance or flag a post to be deleted.
Thanks Anju of the Great Taste. I do realize it's weird. I just started getting bored of the usual cute girl being sexy images. Doing sex scenes isn't really my thing and I'm not good enough to portray any dynamic scenes where the characters are doing more than just posing. So expect more weird posts from me from time to time.
Mda. Among the deleted posts there are a lot of good ones. The approvers do their job perfectly well, sifting out the low-quality pictures from the shit (no)...
Nice check. Deleted this one because of a minor detail and approved this one: post #46919 and this one: post #33303 and this one too... post #38489 Cringe...
I realized you can redraw parts of the AI generated image but for some reason the dumb bot decided to add that black line to the masterpiece and I just noticed it after uploading.
I can retry in 3 days if you delete this mods, one leg has a relict of some swimwear too. I'm on a mission to perfection. Just leave me some uploading capability lol
Yes, the positive prompts include "drinking vodka". It does not appear because the Lora does not recognize it but... it seems that for some reasons it helps
It's hard to find the model used for images that are uploaded from Twitter/Pixiv unless the artist has specified it in their page/it's a self upload, or if the metadata is included.
The metadata here does exist but I can't find anything about a model called "Chiruchiru7" so it might as well just be a private model. But anyway, keep in mind that the uploader who uploaded a Pixiv/Twitter image most likely won't have an idea of the model used unless they already added it.
