Honestly, just trying to figure out different ways to use Stable. The use case is actually not the 360 part of it, it is using a 3d modeling program with Stable Diffusion to create consistent characters. I just got really stubborn and decided to try to make it work in 360. (As far as viewing it, downloading the image and using RenderStuff.com will let you pan the image, and view it in VR if you have a headset).
- Sep 26, 2017
- 327
- 480
Does anyone know of some good prompts for female masturbation? I trying to do either pussy rubbing or fingering but I can't find anything and the prompts I'm trying ain't doing jack shit.
- Jan 24, 2020
- 1,401
- 3,793
Sexual acts can be very problematic with prompt only, this is when we need to use the help of a
Lora or Ti.
You must be registered to see the links
You must be registered to see the links
You must be registered to see the links
- Dec 31, 2016
- 316
- 708
install libbz2-dev. You might need to reinstall python, depending on how you did that initially
So, how many people have had luck with participatory sex? Even with LORA's I often find there's just a lot of dross in it. Has anyone tried using control net on sex-act images?
- Jan 24, 2020
- 1,401
- 3,793
About what now? Are you really expecting anyone to know what you are talking about?
Yes it's possible to write here, the thread is full of posts..
You didn't want to start writing but did it anyway, without any thought whatsoever. This is what you did wrong..
Just spit it out and people in this thread are happy to help.
Last edited:
Only thing I've seen is the notes page for the model on Civitai, but that's hit or miss depending on the creator.
You must be registered to see the links
This addon will help populate the tags from the Civitai data, but it only seems to work on LoRA models.
- Sep 24, 2017
- 260
- 1,093
this is a very handy tool indeed but what I'm looking for is different, kinda looking for a way to translate a prompt from a model to another, to get the same poses and body features and clothes in different art style
edit: after some looking around I found this https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-9962247 and this https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-9964228
some words in the prompt didn't do anything to the images generated with some models but worked with others, maybe there're some alternatives to those words that work with other models (for example big boobs work for a model but for another you have to write big chest or breasts ...etc)
Last edited:
- Jan 31, 2022
- 211
- 631
I would use canny or openpose to keep the pose in the examples you gave.
You just add the image you want into controlnet, and tell it that your prompt is more important ( if you use canny), that should be enough to get roughly the pose you want.
Keeping the pose you can use controlnet - openpose, the preview this generates can work with full body, hands and face and you can apply it to new images.
I'm pretty sure theres a way to keep the style of clothes as well, I'll let you know when I find it.
- Dec 31, 2016
- 316
- 708
Clothing, hairstyle/length, "sizes" and loads of such things won't be consistent between seeds on the same model so only way they'll be consistent to a different model is if they are built on the same data and even then it's a matter of what else is involved.
Generate a few thousand images on the same prompt and you'll see there can be a massive variance within the same model.
It's also very common that words will be completely ignored, it doesn't mean the model "doesn't know them", if you look at the images and prompts shared just in this read you'll see it's rather common that there's things clearly specified in the prompt that's not in the image, but if you keep those in the prompt and remove other elements it'll "pop up".
If you suspect the model might not "understand" something you just need to run just that as a prompt (in some cases you might need a very minimal additional prompting), generate a somewhat large amount of images (can be small and low quality for speed) and see what the more consistent imagery is. You might end up being pretty surprised what actually works, i've had some more "technical/obscure" things show very well, while things we'd normally consider extremely basic fail completely.
If you want absolute consistency you're gonna need something trained, but relatively basic/common concept should work across models, specially if they are within the same "family". Generating across multiple models with multiple images in each, you'll see more variance within the seeds than models that's built on the same data. Unfortunately massive grids like that isn't easily shared here, but you're probably better off generating them yourself anyway so it fits your preferred models and way of prompting
Generate a few thousand images on the same prompt and you'll see there can be a massive variance within the same model.
It's also very common that words will be completely ignored, it doesn't mean the model "doesn't know them", if you look at the images and prompts shared just in this read you'll see it's rather common that there's things clearly specified in the prompt that's not in the image, but if you keep those in the prompt and remove other elements it'll "pop up".
If you suspect the model might not "understand" something you just need to run just that as a prompt (in some cases you might need a very minimal additional prompting), generate a somewhat large amount of images (can be small and low quality for speed) and see what the more consistent imagery is. You might end up being pretty surprised what actually works, i've had some more "technical/obscure" things show very well, while things we'd normally consider extremely basic fail completely.
If you want absolute consistency you're gonna need something trained, but relatively basic/common concept should work across models, specially if they are within the same "family". Generating across multiple models with multiple images in each, you'll see more variance within the seeds than models that's built on the same data. Unfortunately massive grids like that isn't easily shared here, but you're probably better off generating them yourself anyway so it fits your preferred models and way of prompting
- Jan 24, 2020
- 1,401
- 3,793
Don't overlook a tool that is included in SD by default, prompt matrix. It's in the scripts menu. Very similar to xyz plot but instead of comparing generation settings you will compare prompt tags, lines or styles or artists names etc. Write your prompt and have the variables separated with vertical lines ( "|").
Example: |variable1|variable2|variable3| etc.
Example: |variable1|variable2|variable3| etc.
You must be registered to see the links
You must be registered to see the links
You don't have permission to view the spoiler content.
Log in or register now.
Last edited:
- Mar 17, 2021
- 305
- 1,039
For consistent hairstyles or clothes, a good way is use BREAK.
A simple example:
blonde braid haired BREAK woman BREAK wearing blue summer dress BREAK at the sea BREAK high quality
This work like a charm keeping hairstyles and dress. remember the BREAK need used with uppercase char.
Also use it in your negative give really different result, especially if you use long negative.
BREAK is use to subdivide concept, and in many of my test it works like these order:
hairstyles BREAK subject BREAK clothes BREAK background BREAK image details (cinematic, film still, etc...)
this is a simple sample and maybe it need adjusted by checkpoint you are using.
- Jan 24, 2020
- 1,401
- 3,793
I wanted to compare a few different media types or "styles" for a prompt. When attempting to use prompt matrix I discovered that it creates very many images (32). This would take too long so I reverted to something I have used in the past, S/R prompt in xyz plot. S/R (search and replace), it's an option in xyz plot that you can find in scripts menu. It finds a prompt tag or token in your prompt and replaces it with variations that you decide. It generates an image for each variation in a grid and induvidual images as well.
Example
Prompt: blue sailboat, ocean, sunset.
You set the first tag in the script that it should find in the prompt and then replace and the variations after separated with comma.
S/R: blue, red, wood, old pirate, small, large,
gives these variations:
-blue sailboat, ocean, sunset.
-red sailboat, ocean, sunset.
-wood sailboat, ocean, sunset.
-old pirate sailboat, ocean, sunset.
-small sailboat, ocean, sunset.
-large sailboat, ocean, sunset.
It doesn't matter where the tag or token is in the prompt, or if it's one word or a phrase.
- Dec 31, 2016
- 316
- 708
Logically that would only really make a difference if there was something else in the prompt affecting it, IE in the sense of things getting the wrong color, your white top becoming blue, because of the blue shorts. It shouldn't really affect that the simple bikini keeps changing "style", nor that things like a braid or split in the hair keeps changing sides. Nor that your chin length hair changes length drastically between seeds.
Try a relatively simple thing like ombre hair and see how that changes between seeds.
A bit of a warning about using BREAK, there's a lot of extensions that highjack that word so make sure to check which of those are active. Most commonly i think this applies to extensions that allows sectioning or composing to render different prompts in different areas etc.
- Dec 31, 2016
- 316
- 708
As a followup, i'd say it doesn't seem like it has any real impact and definitely not what i'd class as "consistent".
Granted it's only 240 images, but there seems to be a fairly low amount of images that visibly has the three elements hair, top and pants correct
(recommend opening the image in a separate tab due to size, tried to keep it as clear as possible while keeping within upload limits)
Granted it's only 240 images, but there seems to be a fairly low amount of images that visibly has the three elements hair, top and pants correct
(recommend opening the image in a separate tab due to size, tried to keep it as clear as possible while keeping within upload limits)
You don't have permission to view the spoiler content.
Log in or register now.
- Dec 31, 2016
- 316
- 708
For the sake of completeness, i ran basically the same prompt using an extension partitioning the image into 3 areas, top, middle, bottom.
Generally this make it easier to "force" things assuming what ever you are creating can actually fit with the "pieces" you make.
While it's considerably more consistent with the colors of top and pants, you see there's still some problems, hair is better too, but still quite a few misses. You can probably fix this with weighting as the prompts are limited to each section, unlike normal, so the weighting wouldn't be as likely to bleed into other areas. I didn't do that in this case because i tried to keep the prompt (and weighting) the same for comparison.
Image width (aspect) was changed because there was a lot of decapitations which made seeing the hair a bit of an issue.
Generally this make it easier to "force" things assuming what ever you are creating can actually fit with the "pieces" you make.
While it's considerably more consistent with the colors of top and pants, you see there's still some problems, hair is better too, but still quite a few misses. You can probably fix this with weighting as the prompts are limited to each section, unlike normal, so the weighting wouldn't be as likely to bleed into other areas. I didn't do that in this case because i tried to keep the prompt (and weighting) the same for comparison.
Image width (aspect) was changed because there was a lot of decapitations which made seeing the hair a bit of an issue.
- May 18, 2018
- 197
- 2,002
- Mar 17, 2021
- 305
- 1,039
try some upscaler in extra tab, some in this
Step i use:
1)using a denoise model in extra tab and set upscale at 1.1 (using different denoise model based on type of image)
2)resend output image to extra tab and upscale it at 2x with good upscaler model
3)if look good keep, else resend 2x image to extra and redo step 1.
The trick is use denoise with low ratio upscale(1.1) and upscale 2x every time.
So if you want 6x upscale, you have to repeat step 3 times.
You must be registered to see the links
maybe help you.Step i use:
1)using a denoise model in extra tab and set upscale at 1.1 (using different denoise model based on type of image)
2)resend output image to extra tab and upscale it at 2x with good upscaler model
3)if look good keep, else resend 2x image to extra and redo step 1.
The trick is use denoise with low ratio upscale(1.1) and upscale 2x every time.
So if you want 6x upscale, you have to repeat step 3 times.