He was just going to say that self uploads need to be tagged self upload and need and artist tag which could be artist:mango_(artist) or something else if you have another social media account.
Man, I forgot how good this one was. Guess I can eat my words from months ago when I was wondering if AI could actually do pixel art that looked anything like this.
If your curious as to why sex toy is a negative prompt, I cooked this with image preview on, and saw that it kept putting a dildo in the place of the penis, and then as the end step the toy would turn into a dick coming out of her vagina. Putting in the negative prompt stopped that completely.
I really want to release it, in fact, I want to do LoRAs of other PC-98 characters. but I think this LoRA can be improved a little bit more. give me some more time and I'll release it.
Wow! You are the first to tell me that and it's trully great to read :) I am thrilled that my pictures would have such effect on someone. I would glady be of any help on discord if you want. I don't want to let my discord on public comment so hit me with a direct message when you want. As for the model: it's a custom made merge and I'm not willing to upload it to be honest. But I can give you some pointer if you want.
I love your work. You're a huge inspiration of mine and one of the reasons I decided to dive head first into AI and learning about it. I was hoping you could share some tips or even which model you're using? If you don't want to share it publicly we can discuss over Discord or e-mails. I'm just a huge fan. Thank you for all that you do.
Anyway, Wakamo's really grown on me so I was happy to find some really good image of her to upload here and hopefully I can find a lot more in due time.
tags that should be used are "touhou, tru, 1girl, toramaru shou, short hair, blonde hair, streaked hair, red dress, shawl, (tiger print: 0.9), long sleeves, white sleeves, (orange ribbon: 1.2), (hair ribbon), holding, bishamonten's spear, yellow eyes,"
What model did u use ? Can I get a guildeline or more info how to reproduce this picture ? I freaking love it and use it as my phone wallpaper, I want to do more of her.
Keep changing the rating all you want, I'm just gonna change it back. Would do you well go to outside, maybe you'll realize that the tiny bit of cleavage shown here is insignificant compared to what women have been wearing for the past 20 years.
Keep changing the rating all you want, I'm just gonna change it back. Would do you well go to outside, maybe you'll realize that the tiny bit of cleavage shown here is insignificant compared to what women have been wearing for the past 20 years.
Here is a some information, the idea of generating this is based on this other post #16986 I liked the idea but novel AI currently looks very obsolete.
first I generated some images of Saki and Yachie being alone, I used the loras of Saki and Yachie created by Imagine Breaker
then I used IMG2IMG + DPM++ 2S a Karras sampling method to blend the background into a single one. this was the most difficult part because some things the AI redrew better, but other parts were worse, it happened a lot with the face or the skirts. after generating 63 different images, I chose this last one, ironically 63 is my lucky number. https://cdn.discordapp.com/attachments/1042523770360967238/1109310593355227168/00065-SomethingV2_2_1326128075.png
then I used inpaiting to add Yachie's turtle shell and dragon tail, and improve Saki's wings and horse tail, this is the final result alternatively I made a different version that includes a hand drawn Lightning glare by me.
and before you say anything else, I improved the fingers on both versions, it's not perfect, but it's better than broken fingers.
Probably thanks to the combination of loras, without them it looks like this: asset #156407. Foxgirls for the fox god.
I see. That one looks cute too, though I definitely prefer the style of the upload for sure. It's amazing to see how far all of this stuff has come over the last several months.
I don't know why, but it gives me the feeling of having a "colored by markers" style so that's really cool. Also... fox girl, so that's always a huge plus for me.
Probably thanks to the combination of loras, without them it looks like this: asset #156407. Foxgirls for the fox god.
I don't know why, but it gives me the feeling of having a "colored by markers" style so that's really cool. Also... fox girl, so that's always a huge plus for me.
Took forever but I found the proper source. This is the source for the image (3rd image in the set) and the upload here was a very inferior version of it.
I have added an artist tag, it this marshmallow233, you can change it later. please, if you upload something generated by you add that tag + self_upload tag
This author's Pixiv account no longer exists. I just thought I'd post this one to save it from oblivion, since I like it and it doesn't seem to exist anymore. (His Twitter account still exists, but with that dlsite thumbnail at the top of his feed, I'm a bit surprised by that...)
No metadata on this, but I'm guessing it's NAI since a few of his other posts that I have archived have NovelAI metadata.
@tremolo_measure Yup. I used Anything 4.5 model. Metadata might not match 100% cause of inpainting
I have added an artist tag, it this marshmallow233, you can change it later. please, if you upload something generated by you add that tag + self_upload tag
Tag your the images you have generated with self_upload & make an artist tag for yourself (for example gamaz). You can easily change a tag to an artist tag by writing artist:gamaz to the tag box.
I guess shilling for my own model was a success, huh?
Certainly was, I've been dabbling in a few models, this one seems to run pretty well, although it's biased towards a couple things that I wish were more variable (In particular, lighting), it overall has such quality that I'm more than happy with it.
@ANJU Wasn't really my intention here, but it does look like early pregnancy I guess. I just wanted a bit of belly fat (pregnant was still in the wildcard, but wasn't used here).
Also this is my last upload for something like this. I'm going to try other things with this character, as I'm making a better LoRA for this character. In addition this was also an experiment of motion, so she is punching and bringing her arm into her side to chamber for another move like in a martial arts match.
I forgot to put logos and text in negatives. Then this turned out so good that it took me a while to notice after uploading that there are logos all over the bottom. Would delete this is that was an option.
Hey, uploader here. I made a mistake. I mean the Maxwell architecture, not the Pascal architecture. My bad! It has something to do with Cuda 5.x being converted differently, leading to a different starting sampling picture. Anything _starting_ from the Pascel architecture mostly results in the same thing, and I can't wait to try it out when I get my hands on it!
Absolutely no way, this looks amazing! You took my prompt and just made it absolutely beautiful, I was really struggling with it, at some point it just started degrading and I couldn't find the root of it. Love it, great model, good tweaks, and most of all, nice lack of double ears.
Thanks! I saw your commentary about an outdated berrymix and wondered what it would look like with a different model. I really think you should consider upgrading models- a lot of the newer ones are really quite better. Also with negative embeddings you don't really have to go with the giant negative prompt anymore. You can generally just throw one of them in there. The one I used was https://huggingface.co/datasets/gsdf/EasyNegative, but there are a lot.
Absolutely no way, this looks amazing! You took my prompt and just made it absolutely beautiful, I was really struggling with it, at some point it just started degrading and I couldn't find the root of it. Love it, great model, good tweaks, and most of all, nice lack of double ears.
