There were a few things in the original that I wanted to touch up. Wasn't thrilled with how her right hand ended up looking and that it wasn't holding anything. I also didn't care that whatever it was she was eating in the original kinda looked like meat which in this context doesn't make sense since she is trying and failing to make cookies. So I did some touch ups, a few more img2img runs and got a result I'm very happy with.
There were a few things in the original that I wanted to touch up. Wasn't thrilled with how her right hand ended up looking and that it wasn't holding anything. I also didn't care that whatever it was she was eating in the original kinda looked like meat which in this context doesn't make sense since she is trying and failing to make cookies. So I did some touch ups, a few more img2img runs and got a result I'm very happy with.
Mostly a test of the new openOutpainting extension in A1111. Turns out it's well worth playing with; this didn't take long at all, and I can imagine it being easy to put multiple (specific) characters in a scene this way.
@nsokitesu@nohand@aireo2 model is available on the Zeipher discord after joining press this To make it clear: It is free. I use resources other people put hard work into, I can't sell this nor would I.
Wow, this is amazing! unfortunately Zeipher shut down his discord, so there no way for me to get the model. Is there any way you could share the model or your procedure an how to make a similar one?
Is there something better than hentai diffusion, and do you have a guide? I'm just experimenting tbh.
Here's a site with a bunch of models to choose from: https://rentry.org/sdmodels It really depends on what you're going for, and in what style. For me I haven't experimented with many models, but I know that gape NovelAI is better for lewds, and Anything is just great overall, but doesn't do amazing with lewds. Hopefully that helps~
If you are going to go so far as to emphasize child at the beginning of your prompt, then you should be tagging your upload as loli. It along with guro and bestiality are required tags for obvious reasons. Please use the tag in your future uploads. See topic #112 for more on the topic if you are unaware.
You described very well one of the main reasons I dislike a lot of AI images. I would be posting a lot more of the images I find if they just had better hands D:
On the other hand, it makes me appreciate the people who go and make the extra effort to inpaint and/or edit the hands to be beautiful even more.
Hopefully I can become one of those artists you appreciate :3 Been working real hard to prompt craft these in these recent times~! And purrfect every little thing ab a render~! Tagging others posts really helps learn how to spot every little detail~
Hi. I'd be delighted to know the settings you used for generating this image (and for post #11980) โ the sampler, the cfg scale, etc., as they're not included in the metadata for some reason. Well, if you're willing to share the settings, that is.
I think this is so cute but.... Man, once you see those 6 fingers you really can't unsee them...
You described very well one of the main reasons I dislike a lot of AI images. I would be posting a lot more of the images I find if they just had better hands D:
On the other hand, it makes me appreciate the people who go and make the extra effort to inpaint and/or edit the hands to be beautiful even more.
Hey, could you add the models you used as a tag? That would be appreciated as well! If this Eimis is a new model tag, you can create it by doing model:eimis_(model).
I have one question, do you still have something in the options that I should set to show the picture as you have it, such as hybernetwork
I didn't use hypernetwork eta (noise multiplier) for ancestral samplers : 1 Clip skip : 2 You should have check these options in setting And in this picture, I used variation seed(similar to img2img) and crop the image to delete the letterbox I will write specific parameters in the description later. You'll be able to create an image that perfectly matches it
Hey, could you add the models you used as a tag? That would be appreciated as well! If this Eimis is a new model tag, you can create it by doing model:eimis_(model).
Thanks you! It's amazing also, you are using textual inversion to generate the argentina shirt? or something else? i don't have too much lucky with my generations
I also struggled to get a good shirt, so i just generate a lot of images until i find a good one
Thanks you! It's amazing also, you are using textual inversion to generate the argentina shirt? or something else? i don't have too much lucky with my generations
Todavia estoy entrenandolo y probando (todavia se ve que le falta mucho), pero no creo que vaya a tardar mucho. En cuanto lo tenga, publico el link por aca
THIS IS SO COOL WHAT THE HELLLL??? It's not just cute but LITERALLY PERFECT Thank u for this.
Of course! I like to upload cute and high quality post so hearing someone not just love my uploaded post but share my taste is really heartwarming to hear ^^
Thank u guys~!!! <3 I sadly don't have access to my computer right now but... Early in Jan I'll start working on and posting more. Maybe there will even be a doujin starring this character~ Hehe~ x3
First of all, even though u wanted blue clothes I think this is still super cute... But I'm pretty sure for some reason eye color can affect clothes... I used to do this thing where I would add an extra eye tag, so... orange eyes, (deep detailed shiny orange eyes) it would cause my output to have orange clothing features... now if I changed it to something like orange eyes, (deep detailed shiny pink eyes) it would cause the output to have orange eyes, but pink clothing features... Not sure why this is but maybe try messing with negative prompts and you'll get a more finetuned result to what you're looking for. Either way, super cute, and hope to see more like this in the future~ :3
I did see the white hair girl one one and was happy that it has metadata, but what is this "Touhou" server I keep seeing people talking about. I'm thinking of the "Touhou project" when people mention it, but have no clue much further than that. If it's some sort of discord server or something that people share prompts and models on, I'm all in for it. Very curious to start deep diving into more models since I've only really experimented with a few.
You could try to ask it in the Touhou server, they did provide the prompt for the white hair girl one so they might be willing to give the metadata for this one as well when asked, that's how I got the model name as well ^^
I absolutely love the hair here as well, but it's a shame that there is unnecessary stuff like 3 straps & weird black mask strap over there. Otherwise, it'd be an instant favourite from me.
I did see the white hair girl one one and was happy that it has metadata, but what is this "Touhou" server I keep seeing people talking about. I'm thinking of the "Touhou project" when people mention it, but have no clue much further than that. If it's some sort of discord server or something that people share prompts and models on, I'm all in for it. Very curious to start deep diving into more models since I've only really experimented with a few.
Yeah, I didn't mean this as plagiarism. Credit goes to elo0007master for the original prompt.
Hey I appreciate that and I'm sure he does too but, its only really "plagiarism" when u don't post the metadata... No need to credit unless ur a stinky no metadata user... As long as someone posts the metadata in it, its free reign~! He was actually happy to see others using and editing his prompt :) So thanks~ <3
Both of these posts are super outstanding. Extremely detailed, and love the style. Appreciate the metadata, and with it you can really see how deep these prompts are. Glad I could tag these. Keep up the good work and hope to see more posts like these in the future.
Kinda sad how this is likely not going to get approved and taken down... :c Just wanted to spread some lewder astolfo cuz there isn't much on here. Guess others don't wanna see that...
If you're curious... The owner of the original prompt has a custom (cutesexyrobutts) hypernetwork to create stuff in that style, thats why that tag is there. I also think bad_prompt_version2 is a custom list of "bad prompts" Other than that though, seems like it turned out pretty well, and cool to see others experimenting with peoples prompts!
Yeah, I didn't mean this as plagiarism. Credit goes to elo0007master for the original prompt.
From my knowledge, ((its emphasis!)). So the more brackets, the more its emphasized over others in the prompt (i think). Im not 100% sure what {} mean, maybe its the same? But for 300 renders this is pretty awesome honestly. U can even do things like details for tags, such as.... multicolored hair:<(black hair), red hair> cat tail:<tail raised> That sorta thing. Good luck with your future renders~! Hope to see sum on here :3
thanks, this is a great tip. the hair:<(black hair) syntax doesn't always work - but a lot of the time it does, this makes writing prompts a lot easier as it's not so random
This ones so cool... The stained glass in the background, and the eye with her... Much attention to detail, Very very impressive JUST WISH THERE WAS METADATA GRRRRRR
try "stained glass+indoors" these two tags give cool results. sorry for not giving you the metadata, but I simply don't know, I haven't generated the image and extractmetadata.com doesn't shown anything.
From my knowledge, ((its emphasis!)). So the more brackets, the more its emphasized over others in the prompt (i think). Im not 100% sure what {} mean, maybe its the same? But for 300 renders this is pretty awesome honestly. U can even do things like details for tags, such as.... multicolored hair:<(black hair), red hair> cat tail:<tail raised> That sorta thing. Good luck with your future renders~! Hope to see sum on here :3
Uwaaah~~ These detailed mask prompts r super awesome :3 Wish there was metadata... :c
You could try to ask it in the Touhou server, they did provide the prompt for the white hair girl one so they might be willing to give the metadata for this one as well when asked, that's how I got the model name as well ^^
I absolutely love the hair here as well, but it's a shame that there is unnecessary stuff like 3 straps & weird black mask strap over there. Otherwise, it'd be an instant favourite from me.
the child was approved, and the parent is ignored for 3 days -_- this is the only reason why I even posted on the forum
There's a reason for it above the post... Kinda surprised that that's a reason though. Thought it would be more freebase and only based on if the images are TOO explicit to be posted (like realistic loli stuff). But yea I guess its since the hand is bad, but I've seen hands that are much worse on here. Maybe try fixing the hand with inpaint or something and re post it. Good luck to ya~! :3
This ones so cool... The stained glass in the background, and the eye with her... Much attention to detail, Very very impressive JUST WISH THERE WAS METADATA GRRRRRR
If you're curious... The owner of the original prompt has a custom (cutesexyrobutts) hypernetwork to create stuff in that style, thats why that tag is there. I also think bad_prompt_version2 is a custom list of "bad prompts" Other than that though, seems like it turned out pretty well, and cool to see others experimenting with peoples prompts!
I guess its up to the mods when/if they want to approve things... Sometimes it takes longer for them to approve lewder posts? I don't see how this is against any guidelines, so... Hopefully it'll be approved~!
the child was approved, and the parent is ignored for 3 days -_- this is the only reason why I even posted on the forum
I guess its up to the mods when/if they want to approve things... Sometimes it takes longer for them to approve lewder posts? I don't see how this is against any guidelines, so... Hopefully it'll be approved~!
Almost all uploads sourced from various sites (i.e., Twitter and Pixiv) strip the metadata AIBooru displays for posts, unfortunately. Edit: (I *THINK* they do, but I'm not 100% sure.)
Iโve learned it from someone saying that โWe can use [+++tag+++] as placeholders to increase the imput amount of the tag so that its rendering degree will be boosted.While using [] will change the weight,using square brackets in Chinese ใใwould be better.โI found it works to some extent.
I wonder why the AI always makes these same mistakes the Fingers seem wrong and they Fuse with her hand and she has some extra skin on her wrist the Vagina doesn't seem to have an opening For anything and there is an extra crack under it, other than that everything else is excellent IF only it didn't make these mistakes it would be Fap worthy but i can't Fap to it while knowing about these things
There is more, what the heck is on the cupboard and why did it give me a second couch behind the couch she is sitting on. I'm also not happy with the placement of the cum. Why the legs?
But it was more than fapworthy for me, so I wanted to share it. I have more pics like this which I don't upload because they may be worth it for me, but it seems to be enough people who like it here and on sankaku.
I wonder why the AI always makes these same mistakes the Fingers seem wrong and they Fuse with her hand and she has some extra skin on her wrist the Vagina doesn't seem to have an opening For anything and there is an extra crack under it, other than that everything else is excellent IF only it didn't make these mistakes it would be Fap worthy but i can't Fap to it while knowing about these things
How on earth did this prompt produce a giant cock?
It didn't, I used two custom fine-tunes of yiffy18 to get this result. I made them myself. One to get muffet with normal penis, other one to get massive equine cock. And then I refined it, so it lost more tags unrelated to the last things I refined with inpainting.
Good question! I can't confirm this for sure (and I don't have access to my computer to recreate it based on what I think the model is but) but I believe it's probably the anything v3 model.
I say this because sola's work seems to be somewhat consistent in terms of style, and one of their Post reminds me a lot of Another post because it's similar. Then, because that other post with yor briar was similar to my own, in which I used the anything v3 model. So essentially, though connetcing three post that are similar enough, I am guessing it's the anything v3 model. I also used the model with hundreds of (specifc types of) post and it looks like that model in general.
Since this is my workflow: 1. BerryMix / AnyV3 50/50 - do it a few times, take the best and put into: 2. IMG2IMG Noise 0.75 Any / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 3. IMG2IMG Noise 0.5 Berry Mix - do it a few times (also change prompt and/or weights), take the best and put into: 4. IMG2IMG Noise 0.35 Berry / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 5. IMG2IMG Noise 0.2 + Depthmap + Upscale Berry Mix / AnyV3
Prompts change - the ones that are always there for this batch:
masterpiece, high quality, volumetric lighting, cg wallpaper, sitting, living room, completely nude,
than
(huge breasts:1.x), (oppai loli:1.x), (young face 1.x), (school collar necktie:1.x), (socks and sneakers:1.x), (wet:1.x), (spread legs:1.x), (erect nipples:1.x), (bored but curious expression:1.x),
but again, these change and sometimes I add something to remove it again. Like berry tends to make too many nipples with giving erect nipples too much weight. So I swap that out, sometimes I remove wet completely because it creates artifacts in anyf222. So there is no coherent prompt, I'm sorry.
I like this style very much, can you share the prompts please?
Since this is my workflow: 1. BerryMix / AnyV3 50/50 - do it a few times, take the best and put into: 2. IMG2IMG Noise 0.75 Any / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 3. IMG2IMG Noise 0.5 Berry Mix - do it a few times (also change prompt and/or weights), take the best and put into: 4. IMG2IMG Noise 0.35 Berry / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 5. IMG2IMG Noise 0.2 + Depthmap + Upscale Berry Mix / AnyV3
Prompts change - the ones that are always there for this batch:
masterpiece, high quality, volumetric lighting, cg wallpaper, sitting, living room, completely nude,
than
(huge breasts:1.x), (oppai loli:1.x), (young face 1.x), (school collar necktie:1.x), (socks and sneakers:1.x), (wet:1.x), (spread legs:1.x), (erect nipples:1.x), (bored but curious expression:1.x),
but again, these change and sometimes I add something to remove it again. Like berry tends to make too many nipples with giving erect nipples too much weight. So I swap that out, sometimes I remove wet completely because it creates artifacts in anyf222. So there is no coherent prompt, I'm sorry.
1. BerryMix / AnyV3 50/50 - do it a few times, take the best and put into: 2. IMG2IMG Noise 0.75 Any / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 3. IMG2IMG Noise 0.5 Berry Mix - do it a few times (also change prompt and/or weights), take the best and put into: 4. IMG2IMG Noise 0.35 Berry / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 5. IMG2IMG Noise 0.2 + Depthmap + Upscale Berry Mix / AnyV3
THAT is a delicate touch by the maestro. Thanks for all the detail, man. I really admire it. Keep up the great work!
just wow. What model did you use for this gorgeous masterpiece?
1. BerryMix / AnyV3 50/50 - do it a few times, take the best and put into: 2. IMG2IMG Noise 0.75 Anyv3 / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 3. IMG2IMG Noise 0.5 Berry Mix - do it a few times (also change prompt and/or weights), take the best and put into: 4. IMG2IMG Noise 0.35 Berry / F222 50/50 - do it a few times (also change prompt and/or weights), take the best and put into: 5. IMG2IMG Noise 0.2 + Depthmap + Upscale Berry Mix / AnyV3
Pretty soon the AI will be able to make and post the image by itself. Then it can view the images on its own so we won't have to. Think of all the time we'll save!
Im somewhat new to AI creation. I know the Yiffy,Zeipher models. Are you running several models at the same time in SD or something? Perhaps any Discord you could recommend to read up on it :O ?
It's a merged model, which you can make yourself in the "Checkpoint Merger" tab in webui. It is a bit complicated though, so you'll want to look up a guide.
Im somewhat new to AI creation. I know the Yiffy,Zeipher models. Are you running several models at the same time in SD or something? Perhaps any Discord you could recommend to read up on it :O ?
