This is from a giant script that uses sd-dynamic-prompts in Automatic1111 to generate different scenarios. So there's different professions, hair styles, bondage situations, etc.
If I am going for a specific scenario, it is easy to clean up to get something readable.
@abi_00 Sorry, I missed your comment earlier. Could be a number of things really. I tried the same settings on v12 of realcartoon and it was very similar so it's unlikely that. Maybe it's clip skip or missing embeddings (BadDream is the most important one for the style I think)? Could also be that some of the loras I'm using have new versions and they look different. I think I didn't do anything weird during upscaling so that's not a problem, but maybe you're starting with a different resolution and that makes the faces different. You could always send me the image you're getting, here or on discord and we can troubleshoot from there.
If you're fast enough on the upload (i.e. before the thread gets pushed off the board), the commentary will autofill. Otherwise it'll get autotagged with bad source.
Ahh, okay. Good to know. Cheers for adding source for some. I've added for the rest. Is it standard to add source with the original 4chan.org link or archive links for dead threads? Or does it not matter?
Nope. These aren't mine. That's where I got them though and the thread OP is the artist.
If you're fast enough on the upload (i.e. before the thread gets pushed off the board), the commentary will autofill. Otherwise it'll get autotagged with bad source.
This is one of the best pieces I've see here. I've been trying to replicate this style of face to no avail. I've used the same model version, the newer one, and a combo of the loras indicated below. Any tips?
The software I use for image generation is Stable Diffusion WebUI. I am running this in a Colab Pro environment. If you use Colab Pro as I do, I recommend using the notebook at https://github.com/TheLastBen/fast-stable-diffusion. The model used to generate this image is feathermix. It can be downloaded from the link in the wiki of this tag. I have merged some LoRA into this model and used it.
Can you tell me what ai software you ise as i want to try to make some ai art similar to what you post here and it would be very usefull to have some data to work off of as a start.
The software I use for image generation is Stable Diffusion WebUI. I am running this in a Colab Pro environment. If you use Colab Pro as I do, I recommend using the notebook at https://github.com/TheLastBen/fast-stable-diffusion. The model used to generate this image is feathermix. It can be downloaded from the link in the wiki of this tag. I have merged some LoRA into this model and used it.
Can you tell me what ai software you ise as i want to try to make some ai art similar to what you post here and it would be very usefull to have some data to work off of as a start.
I don't really get the downvotes either but the reason I didn't approve it is that the face and the cum on it looks off - there's a random line on her right cheek and the jaw right below that is dented.
I don't really get the downvotes either but the reason I didn't approve it is that the face and the cum on it looks off - there's a random line on her right cheek and the jaw right below that is dented.
I don't know if the downvotes/disapprovals were due to the image quality itself or something about its content.
I've never really been a huge fan of posts featuring outright sex but I've been loosening up on that and trying not to be too dismissive. Another thing I don't really like is excessive/large amounts of cum (if not for that I probably would've approved) but I don't have a specific quality related reason because the image itself looks fine.
It appears, people do not like this post (getting downvoted a lot). Can I get constructive feedback as to why? So I can improve my AI quality in the future. I'm still pretty new to AI and working on improving my generations. My goal is also understand what exactly this booru is looking for in terms of quality, content type, etc.
I don't know if the downvotes/disapprovals were due to the image quality itself or something about its content.
I've never really been a huge fan of posts featuring outright sex but I've been loosening up on that and trying not to be too dismissive. Another thing I don't really like is excessive/large amounts of cum (if not for that I probably would've approved) but I don't have a specific quality related reason because the image itself looks fine.
It appears, people do not like this post (getting downvoted a lot). Can I get constructive feedback as to why? So I can improve my AI quality in the future. I'm still pretty new to AI and working on improving my generations. My goal is also understand what exactly this booru is looking for in terms of quality, content type, etc.
Note, Novelai has a "add charismas sprit" option, which does this. It is why the charismas tag is added despite not having any charismas related things in my prompt.
I've also been told that people dislike when the metadata is removed, so I'll refrain from doing that unless it's not my AI I upload.
