- Dec 21, 2020
- 1,575
- 3,776
- Apr 23, 2019
- 879
- 1,672
Whoa! This is crazy impressive
& crazy scary if you think about it, pretty much the end of non-anon/digital face protection social media, cause we all don't have an Uncle Ben event in our lives to realize "With Great Power, comes Great Responsibility" and we getting there very shortly.Most interesting that the Adult Video stars have the most "not correct" feel (face fit I mean) while the normal actresses have the very "viable" realistic feel. Is it just me or do you agree Mr-Fox? I wonder if it's because our brains have seen AV stars already nude more and causes the difference or is it something else?
Just curious how long did it take to make so many variations?
- Jan 24, 2020
- 1,401
- 3,804
short answer: a veeery long time..Whoa! This is crazy impressive
Most interesting that the Adult Video stars have the most "not correct" feel (face fit I mean) while the normal actresses have the very "viable" realistic feel. Is it just me or do you agree Mr-Fox? I wonder if it's because our brains have seen AV stars already nude more and causes the difference or is it something else?
Just curious how long did it take to make so many variations?
Since it did take a long time I learned a lot and also they are not posted in the order I made them. So it could just be that I did a better job on some than others. I'm glad you liked it.
- Sep 26, 2017
- 397
- 623
Is this from using a checkpoint or lora? Where can I get it lol? I can't find any decent loras that let me do nswf images of celebs.
I end up having a habit looking at the fingers to see if it is AI generated lol
- Jan 24, 2020
- 1,401
- 3,804
It's made with an extension called roop, not a lora.
You must be registered to see the links
Follow the installation instruction, it won't work otherwise. After the installation you need to edit a code inside a py file to turn off the NSFW filter. In Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-roop\scripts edit cimage.py and replace the code with this:
" import tempfile
def convert_to_sd(img):
return [False, tempfile.NamedTemporaryFile(delete=False, suffix=".png")] "
Last edited:
- Jan 24, 2020
- 1,401
- 3,804
It's not bad but needs more work imo. In the first image the faces on both are a bit wonky. Is she supposed to look pregnant? This happens sometimes with loras or Ti's, an unwanted side effect with swollen belly. I read the prompt, omg that's some beautiful ChatGPT prose..
I don't think you need to explain the abbreviation "milf" in the prompt, it's common enough and also we are not communicating with some singularity. SD is simply in data and out data.. Even though it hurts the soul, I would simplify that prompt as much as possible. It's not practical to have such a large describing prompt. A lot of redundant words and that has no effect. It's impossible to know what in the prompt affects what in the image. Though I know easy negative etc is popular I think it's better to try to use normal pos and neg prompt instead. You can only adjust the weight of Ti's like easy negative, you have more direct control with normal prompting. I think my main advice is, "more" doesn't equal "better". With SD it's the opposite but should be worded "simpler is better". I'm also guilty of writing large prompts but I think this is some kind of record. Also if you insist on using any lora or Ti, don't use so many, it's difficult enough to get one to work properly.I hope this helped and is not interpreted as something overly negative, it's only meant as constructive.
- Dec 31, 2016
- 316
- 708
negative prompts are much less needed than ppl think, you're generally better off starting without them and being specific in your positive prompt.
IE using age to avoid the person being too young or old, or the type and quality of photo.
Negatives mostly come into play to combat "conflicts", like when you're specifying colors that has a habit of coloring everything or the switching place with another color. In those cases you'd use negatives to "disallow" the color on the specific thing.
Alot of these "easy this and that" flood prompts with pointless instructions which most likely has negative impacts on your image. One very basic example would be if you're trying to create something that's dirty, in ruins, "dystopian" etc, and your "easy to use prompting" contains negatives like ugly and/or old.
Start with a simple positive prompt, find the basics you want and work on finding a specific seed you like (optional in many cases), then tweak/expand upon your positive prompt and if you encounter persisting "problems" you can start trying to add some very specific negative prompts.
With the, worryingly high, amount of images i've generated so far i'm seeing very clear signs that negative prompts are byfar less needed than "guides" and "all knowing super important creators" make it out to be.
As Mr-Fox mentioned, stick to the good old
IE using age to avoid the person being too young or old, or the type and quality of photo.
Negatives mostly come into play to combat "conflicts", like when you're specifying colors that has a habit of coloring everything or the switching place with another color. In those cases you'd use negatives to "disallow" the color on the specific thing.
Alot of these "easy this and that" flood prompts with pointless instructions which most likely has negative impacts on your image. One very basic example would be if you're trying to create something that's dirty, in ruins, "dystopian" etc, and your "easy to use prompting" contains negatives like ugly and/or old.
Start with a simple positive prompt, find the basics you want and work on finding a specific seed you like (optional in many cases), then tweak/expand upon your positive prompt and if you encounter persisting "problems" you can start trying to add some very specific negative prompts.
With the, worryingly high, amount of images i've generated so far i'm seeing very clear signs that negative prompts are byfar less needed than "guides" and "all knowing super important creators" make it out to be.
As Mr-Fox mentioned, stick to the good old
You must be registered to see the links
- Dec 31, 2016
- 316
- 708
i don't have access to the UI atm, but generally in the seed/sampler node you have 2 fields, one for the seed number and a text/select one, can't remember the wording on it but when you click it you get the option to select "fixed". Default is some wording of "random seed after generation"
- Dec 31, 2016
- 316
- 708
Fraid not, i've only done some limited screwing around with comfy.
Trying to find consistency in training and getting one "generator" to cooper is taking enough time, specially on a slow spec comp, so haven't really had the time to do much with comfy.
The nightmare of trying to pick the best out of a training.... Generally you hope for a bunch of poor results and one that stands out, this grid is among the more varied ones for this training....the closeup face shot grid is hopeless to figure out
(great, image gets resized, probably due to width i guess, it's barly over 15k px....kinda makes it a bit pointless
)
Last edited:
- Dec 21, 2020
- 1,575
- 3,776
- Dec 21, 2020
- 1,575
- 3,776
Cycle Through Models / Samplers in ComfyUI
Say you want to use same seed but cycle through samplers:
Say you want to use same seed but cycle through samplers:
- Right click on "KSampler", then chose convert sampler_name to input.
- Add node called "primitive" to the workspace.
- Connect the node "primitive" to the "sampler_name" of the KSampler - you will see how this node "primitive" changes its look and gets additional fields.
- Change the field "control_after_generate" in the node "primitive" to "increment".
- Jan 24, 2020
- 1,401
- 3,804
I agree with most what you said but I also completely disagree..
I think that negative prompting is a very powerful tool if you utilize it properly and is very much essential. Easy negative and the likes is a bad and lazy way to go about it though. It's a bit like hitting SD over the head repeatedly while screaming "make nice picture" over and over and think this will get you what you want. Negative prompting is not only for "conflicts", it's all about tags for what you don't want to see in your image, but also a way to "guide" the image in the right direction. It becomes especially powerful when used in combination with the positive tags.Example
pos: huge boobas
neg: small boobas
Now by utilizing the neg you have increased the weight for huge boobas substantially.
Example2
pos: photography
neg: cartoon, painting, 3D, Render, Anime, Hentai, sketch etc
Now you have specified the image medium much more clearly.
Negative prompting is very much an essential part of generating ai images, just need to utilize it in a good way and not use neg lora's or Ti's etc.
- Dec 31, 2016
- 316
- 708
I'm gonna take the risk that the previous image posting was due to no prompts, apologies if it wasn't. So fingers crossed i'm not pissing off creators, mods and everything.
You don't have permission to view the spoiler content.
Log in or register now.
- Jan 24, 2020
- 1,401
- 3,804
I loved holiday island and especially Yvette. Before training my Kendra Lora I made a failed attempt at an Yvette Lora.
Try your prompt with Kendra, it should give some interesting result. You probably need to use a low weight and possibly adjust the prompt a bit. She is quite thick in comparison with Yvette but if you adapt the prompt you will get the huge boobas from her.
You must be registered to see the links
Last edited:
- Jan 24, 2020
- 1,401
- 3,804
I created an image of Yvette way back with img2img, before I really had a clue.
You don't have permission to view the spoiler content.
Log in or register now.
And also Dr Rosario, that I never posted here.
You don't have permission to view the spoiler content.
Log in or register now.
- Sep 26, 2017
- 397
- 623