Just to be clear: no it's not Kagome from Inuyasha and if you watched the show you'd know. Stable Diffusion is not great at re-creating established characters (which indeed sucks)
@antlers_anon are you sure there's no hypernetwork you've selected in your settings tab, or TI that's being used to generate this image?
I tried to generate this with your provided mix__2.ckpt with all of the exact same settings (prompt, sampler, CFG scale, seed) and it still results in a fairly realistic non-anime style.
If nothing else, would you be willing to share your embeddings folder and hypernetworks folder? (just a screenshot would probably do as well?)
edit: looks like the firstpass width/height was set to 0x0, so it was just straight-up going for 768x1280 for initial resolution. I ended up finding that it gets pretty close, especially if I use kl-f8-anime2.vae instead of novelai/anythingv3 vae.
I'm guessing that colour correction and some filtering adds a little noise
I was gonna make a meme comment, but I feel like being helpful. :u
Being a Builder gives you access to a few additional features regular users don't have, like using the mode menu when viewing posts (for quick faving/unfaving, and using tag scripts) and you can give other people feedback, to name two of them... and since the Gold and Platinum levels are... sort of used, I guess (but not really?) Builder is kind of the default level that people get promoted to if they're active in uploading and tagging stuff, I suppose.
Oh I know that now. But this pic is actually an accurate representation of how I felt when the message came in. I was like, "Oh cool! I'm a builder! ....... what's a builder?"
I was gonna make a meme comment, but I feel like being helpful. :u
Being a Builder gives you access to a few additional features regular users don't have, like using the mode menu when viewing posts (for quick faving/unfaving, and using tag scripts) and you can give other people feedback, to name two of them... and since the Gold and Platinum levels are... sort of used, I guess (but not really?) Builder is kind of the default level that people get promoted to if they're active in uploading and tagging stuff, I suppose.
I'd love to know what hypernet was used with this!
I'm almost entirely sure I didn't use anything more than the mentioned model. Did you try using it with the prompt? I can try generating it again to see if I didn't mess up while copying the settings. I'll report back once I'm near my pc.
@SomeCoolUsername Sorry to disappoint, but I don't really have them. I use this to generate, and none of the metadata gets saved automatically. I only fill out what I can know for sure.
The only information that I didn't add to the metadata field that I had access to is the Guidance Scale, since I'm not sure if it's the same thing as Cfg Scale. I tend to go with either 8.5 or 9, I think this one was a 9.
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~
That expression definitely fits Weiss <3 - an astounding picture
Thanks haha, the face probably required the most work. For some reason heavily weighting squinting started putting glasses on her, so I had to heavily weight glasses in the negative. I probably could have just erased the mouth in Krita and drawn a line to let SD see what I wanted but instead I inpainted each side for 15 minutes till I got what I wanted lol
Hey this is actually a problem I've been having. Thanks for mentioning it. I just learned I need to put it in the VAE folder to make it show up on the list.
btw, have you tried using --no-half-vae? it helped me to get rid of black pictures when generating using novelai, anything, etc.
I wouldn't recommend using the Anything VAE since it would cause some images to be black. Most of the time they would be fine but once every, say, 50-60 images I would get a completely black square.
Switching to vae-ft-ema-560000-ema-pruned.ckpt fixed the issue for me.
Hey this is actually a problem I've been having. Thanks for mentioning it. I just learned I need to put it in the VAE folder to make it show up on the list.
I wouldn't recommend using the Anything VAE since it would cause some images to be black. Most of the time they would be fine but once every, say, 50-60 images I would get a completely black square.
Switching to vae-ft-ema-560000-ema-pruned.ckpt fixed the issue for me.
Interesting. I made the exact same model, with an identical hash but with absolutely identical settings and prompt I get not even close to the same art as in the post.
Also, there seems to be some problem with the colors
I can't get the result you're getting. Even though hashes match, models might differ due to the weird way they are calculated. In my experience the hash stays the same no matter what weight you use with the add difference method. So either one of us might have made a mistake there (wouldn't be the first time I messed up writing instructions for a mix). You can download the model I'm using from https://mega.nz/folder/XMUzWIAL#i52o1QYOx7j1neujUJzfWw as mix__6.
I'm also using the latent upscaler for the highres fix. You probably won't get the exact same image because of my --xformers but you should get close.
As for the colors, I think used the vae-ft-mse-840000 one. As redjoe said, it should fix your color problems.
Recently seen some models mention a 'needed' use of different clip skip variables and I wanted to know more about them. Happened to come across this example, thanks 👌
Glad I could help. If you're going to be working with CLIP a lot, I recommend adding it to your main interface. Go into WebUI settings| User interace| Quicksettings list: Add CLIP_stop_at_last_layers (put a comma between each argument here). Refresh and it'll be up top next to your model selector.
Looks great! Would you be willing to share the embedding? How many images did you use to train it? I want to train a Yoimiya embedding, and I selected around 70 images. I wonder if that's enough.
Recently seen some models mention a 'needed' use of different clip skip variables and I wanted to know more about them. Happened to come across this example, thanks 👌
Interesting. I made the exact same model, with an identical hash but with absolutely identical settings and prompt I get not even close to the same art as in the post.
Also, there seems to be some problem with the colors
This is a problem known as "bruising" (the little purple spots here and there). To fix it, go to WebUI settings| Stable Diffusion tab| SD Vae. Set it to anything-v3.0.vae or nai.vae (I'm pretty sure these are identical). I have no idea if this will make your image identical to AA's, but it will fix the bruising and desaturation.
Interesting. I made the exact same model, with an identical hash but with absolutely identical settings and prompt I get not even close to the same art as in the post.
Also, there seems to be some problem with the colors
... I don't like ads too, but it's technically not against the rules as far as I know. (I agree we could add large watermarks to the prohibited content list.)
It's not against the rules, but I'd agree it probably should be.
Posts like the two from this user so far just seem like advertisements for their patreon and people don't come here to look at stuff that only serves to promote something like that.
I'll probably get downvoted for saying this, but I do have a fanbox where people do support me. I'm sure there are some links to it even on this site and yet I don't really feel like a scumbag T_T Calling out aggressive advertisement like in this post is fine. I don't like ads too, but it's technically not against the rules as far as I know. (I agree we could add large watermarks to the prohibited content list.)
I meant the model. You tagged this one as anydream when I'm fairly certain you meant to tag anything
Jesus, I didn't even catch that. Indeed, I did mean anything, because this image (most of it) was made in the same batch as the others I uploaded a few days ago! Thanks for pointing that out
I was about to say that you should be able to check the metadata to see the tags used for making it but it seems I forgot to give the tags for the non-ai scaled version, because I'm certain I had no extra hands but oh well.
Okay I just checked and I did tag no extra hands but didn't emphasize it so maybe that's why
I meant the model. You tagged this one as anydream when I'm fairly certain you meant to tag anything
I suspect that you have mistagged the model you used on this one
I was about to say that you should be able to check the metadata to see the tags used for making it but it seems I forgot to give the tags for the non-ai scaled version, because I'm certain I had no extra hands but oh well.
Okay I just checked and I did tag no extra hands but didn't emphasize it so maybe that's why
oh come on, the floating plates may be unrealistic, but at least they are well made, no anatomy errors or anything like that. I could say that a girl flying is unreal and that alone is also a bad image, come on, that's stupid.
if it is well done, without serious anatomical errors, it deserves a second chance.
There's a difference between disinterest & poor quality.
oh come on, the floating plates may be unrealistic, but at least they are well made, no anatomy errors or anything like that. I could say that a girl flying is unreal and that alone is also a bad image, come on, that's stupid.
if it is well done, without serious anatomical errors, it deserves a second chance.
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) — 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
