|
|
|||
| forums: groups: | |||
|
"a place to post ai content"
Happy New Year to all, may we all be so fortunate to celebrate with these lovely ladies from New Years past and present!
 Love you, too |
|
Love you, too |
|
Love you, too |
|
Love you, too |
|
Love you, too |
|
Love you, too |
I have never had much luck with Microsoft Designer. My prompts didn't work as well as on Bing, I didn't like getting only one image at a time, and I didn't like that there was no save function or even a history of creations, etc. So most of my creations have been made on Bing. Well.... Bing was being slow yesterday, and I was having a good run with a prompt, so I decided to throw my prompt in MD while I wated for Bing to load. Not only did MD generate my tested prompt, it gave me somewhat better natural poses than Bing. So I ran both for a while. Then I tried to do a low camera angle in Bing, and it just wouldn't do it. With not much hope, but nothing to lose, I tried in MD. To my surprise, it worked. Not only did it work, it worked repeatedly. Later I made an attempt to pose my model in Bing. Simple pose, nothing crazy, just trying to get the model to look down. No dice. Ok... let's see what MD does. It did it. Holy shit. So then I got creative abd attempted poses that I've been wanting to do in Bing ever since I started, and usually get met with a hard prompt block for even attempting. It did them. It did them EXACTLY. Wow....
So, my new game plan is to run both in tandom. Bing will be my primay source of images, but I will try to get my "special" images from MD.
All that said, I have not been able to get MD to do anything today. Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later. Not a single image has gone through. So either it's because it's New Years Day and everybody is home from work and playing with the image creator, or I used all of my good luck yesterday, or they are fixing the broken filter that I took advantage of yesterday lol.
These images were created with MD. They aren't nude or anything, and may not be everybody's cup of tea, but they are right up my alley.
So, my new game plan is to run both in tandom. Bing will be my primay source of images, but I will try to get my "special" images from MD.
All that said, I have not been able to get MD to do anything today. Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later. Not a single image has gone through. So either it's because it's New Years Day and everybody is home from work and playing with the image creator, or I used all of my good luck yesterday, or they are fixing the broken filter that I took advantage of yesterday lol.
These images were created with MD. They aren't nude or anything, and may not be everybody's cup of tea, but they are right up my alley.
Hey, I'm following the same principles. Bing can definitely produce more NSFW images but Design is more flexible around prompting.
"Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later"
These errors are generally indicative of a softban or you've hit the daily limit. MS implemented a limit of around 70 gens just before Xmas, after which a cooldown is in action. That cooldown gets longer and long until you can gen nothing.
Other than letting your account reset for 24-30hrs there isn't much you can do about it.
If you repeatedly try and generate with the messages present, you'll lock your account faster.
"Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later"
These errors are generally indicative of a softban or you've hit the daily limit. MS implemented a limit of around 70 gens just before Xmas, after which a cooldown is in action. That cooldown gets longer and long until you can gen nothing.
Other than letting your account reset for 24-30hrs there isn't much you can do about it.
If you repeatedly try and generate with the messages present, you'll lock your account faster.
messg said: Hey, I'm following the same principles. Bing can definitely produce more NSFW images but Design is more flexible around prompting.
"Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later"
These errors are generally indicative of a softban or you've hit the daily limit. MS implemented a limit of around 70 gens just before Xmas, after which a cooldown is in action. That cooldown gets longer and long until you can gen nothing.
Other than letting your account reset for 24-30hrs there isn't much you can do about it.
If you repeatedly try and generate with the messages present, you'll lock your account faster.
"Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later"
These errors are generally indicative of a softban or you've hit the daily limit. MS implemented a limit of around 70 gens just before Xmas, after which a cooldown is in action. That cooldown gets longer and long until you can gen nothing.
Other than letting your account reset for 24-30hrs there isn't much you can do about it.
If you repeatedly try and generate with the messages present, you'll lock your account faster.
I wonder if they freeze you out by ISP then. The account I was trying to use this morning has never been used on there before. This evening I was able to get about 20 generations with thst account and then stsrted getting the "It's us, not you" message again.
moptopumd said:
I wonder if they freeze you out by ISP then. The account I was trying to use this morning has never been used on there before. This evening I was able to get about 20 generations with thst account and then stsrted getting the "It's us, not you" message again.
messg said: Hey, I'm following the same principles. Bing can definitely produce more NSFW images but Design is more flexible around prompting.
"Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later"
These errors are generally indicative of a softban or you've hit the daily limit. MS implemented a limit of around 70 gens just before Xmas, after which a cooldown is in action. That cooldown gets longer and long until you can gen nothing.
Other than letting your account reset for 24-30hrs there isn't much you can do about it.
If you repeatedly try and generate with the messages present, you'll lock your account faster.
"Nothing but messages saying there was an error on their end, or they are experiencing a high volume of creations and to try again later"
These errors are generally indicative of a softban or you've hit the daily limit. MS implemented a limit of around 70 gens just before Xmas, after which a cooldown is in action. That cooldown gets longer and long until you can gen nothing.
Other than letting your account reset for 24-30hrs there isn't much you can do about it.
If you repeatedly try and generate with the messages present, you'll lock your account faster.
I wonder if they freeze you out by ISP then. The account I was trying to use this morning has never been used on there before. This evening I was able to get about 20 generations with thst account and then stsrted getting the "It's us, not you" message again.
I don't think it's ISP related. I was previously running using different proxies for different accounts but haven't felt the need. I've been ok switching between the accounts.
The red "it's not you, it's us" I find is fine to regenerate with mostly. It's the yellow warnings you have to watch for.
If you get a yellow waning immediately within a couple of seconds that tends to be the prompt itself.
If it's more like 8-10 seconds, it's the image filter that's blocking it.
The yellow "Visitors" warning is when you ae hitting a cooldown either due to repeated bad prompts or you've hit the 70ish limit. You need to give it 60 secs+ The cooldown gets longer for each subsequent prompt so at somepoint it's not worth retrying. better to rest the account.
deadpool said: Moptop! These images are smooth! What was the prompt for these? Two in particular are amazing; they're exactly the stuff I was looking for in these AI generated images.
These all used variations of the same prompt. It was something like
"Photographic image of a 20yo female, xxxxxxxxx. Long blond hair appears sleek and straight. Black t-shirt, blue jeans. Clear gunge dumped on head. gunge engulfs hair. Wet hair. Clear gunge drips off of the head and clothes."
The "xxxxxxx" is what I keep changing. "Laying back, propped up on elbows, head tilted back" or "bent forward at the waist, head down, hair flipped to the front and hiding face", or for the last picture I added "low angle" before "photographic image", and the "xxxxxx" was "head tilted down, leaning forward slightly, looking at camera, hair is like a tunnel around the camera"
When that last image popped up, I legit said out loud "What..... the fuck... did I do? Oh my God......"
"It'll be easy", they said. "Just climb into the Jefferies Tube and fix the leak."
So I just discovered something that may help everyone out. Have you created an almost perfect image, spoiled completely by just that one infuriating detail or subject?
Below the Bing image description you'll see " customize " give it a click and after loading briefly look to the upper left of the menu.
Select " generative erase " and you can select any item, artifact or subject you want to remove.
Results below.
Below the Bing image description you'll see " customize " give it a click and after loading briefly look to the upper left of the menu.
Select " generative erase " and you can select any item, artifact or subject you want to remove.
Results below.
Your parents were wrong. Play with your food.
|
Love you, too |
|
Love you, too |
A few muddy highlights from the last few days prompting.
Tip for generating these is to use alternative words, accented letters and as much leading language as possible to bypass the text filters then be persistent with the next level of image filtering. Background "stuff" helps to give the filters more to work through, so that every 5 or 6 goes you get an image. Dangerously addictive! Multiple accounts are handy, I got down to one gen per login pretty quickly so it takes time - luckily something that's been in abundance this last week!
Tip for generating these is to use alternative words, accented letters and as much leading language as possible to bypass the text filters then be persistent with the next level of image filtering. Background "stuff" helps to give the filters more to work through, so that every 5 or 6 goes you get an image. Dangerously addictive! Multiple accounts are handy, I got down to one gen per login pretty quickly so it takes time - luckily something that's been in abundance this last week!
some game show fun where the loser is being setup for their messy punishment, being the loser doesn't seem too bad here
can't wait to try making more of the payoff images
main prompt:
blonde woman wearing frilly latex costume on a game show, there is a screen with the words "Pie That Loser", she looks nervous and is sitting in a chair that has straps holding her wrists and ankles, the chair is surrounded by metal carts lined with big fluffy Chantilly pies, two women hosts wearing clown costumes stand on either side of the carts holding oversized Chantilly pies and looking excited to throw them
can't wait to try making more of the payoff images main prompt:
blonde woman wearing frilly latex costume on a game show, there is a screen with the words "Pie That Loser", she looks nervous and is sitting in a chair that has straps holding her wrists and ankles, the chair is surrounded by metal carts lined with big fluffy Chantilly pies, two women hosts wearing clown costumes stand on either side of the carts holding oversized Chantilly pies and looking excited to throw them
|
Love you, too |
|
Love you, too |
As relatively new to this, I'm rather interested in what gets generated. Of course and I'm sure other are the same, some generated images aren't as good as others, and you do get the odd dodgy anomalie. But I'm still impressed.
I've got a pie, and I know how the throw it.
Kabe22 said:
I'm not sure if any of this will help, but these are things to try:
"beautiful" is generally redundant, as the majority of model photography that the generator was trained on are, well, models. A lot of times when I include "beautiful" in my prompts, I get rather ...voluptuous results. lol I think the AI associates "beautiful" with big boobs, and that could be triggering the sensors.
You may be overdoing it on the wet terms and synonyms. Some of those words ("wetness," and "wet skin" in particular) are used far more commonly in erotica and porn than in normal speech, and that may be triggering the sensors.
I often don't even use any form of wet/drenched/soaked descriptors, and instead rely on environmental effects to indirectly create the wet clothes and wet hair, (but the obviously drenched look has never really been that important to me either, so some descriptors are probably needed for that). "In heavy rain," "splashed by xxxx," or "after swimming" can often do the same thing as all of those references to wetness. Also, moptopumd gave some great advice for getting wet hair without actually saying "wet hair":
And a side question: Your Bing pictures pretty much all have a grainy look to them, with a strange effect on the eyes. Is that intentional? If not, I think that's caused by using "photo" as your image type keyword. I've found that "photographic image" gives clearer images and I have a lot less issues with the eyes.
Finally, I used both my advice and moptopumd's advice to rewrite your prompt to test it all out and got these as results. I didn't make too many attempts because I already use up all my boosts for today on making images for my latest D&D character idea: an orc warrior princess/barbarian wielding a greataxe while wearing a tattered, bloodstained ballgown. As much as I'd love to share some of those pictures, they're probably against the forum rules
This is the prompt I used in Bing Image Creator. The clothing isn't super shiny with rivulets of water, but I also didn't play around with the prompt too much. I just wanted to show it works and give you some idea of what it looks like. I used the prompt 3 times and got 4 images each time, so none were blocked at all. The hair looks realistically wet in all but one of the 12 images, and a few of the images were a little iffy on whether or not the clothes were actually wet. But still, 7 pretty decent wetlook images out of 12 is great odds. This was a quick attempt at a prompt, so with some playing around with it, you could get the full-body shot (putting shoes in the prompt sometimes works for that) with more obvious wetness. I know the patterns or details on the clothing often overrule the wet look, so leaving the floral part out might work better.
"full-length photographic image of a happy woman in a garden on a sunny day washing her hair under an outdoor shower wearing drop earrings and small pendant and 1970's-style wet long-sleeved collared dark navy floral blouse and wet flared turquoise silk floor-length skirt, coated in water, splashing, hair smoothed sleek and flat, full-body shot"
I hope some of this helps!
Edited to add: I just looked at some of your more recent image posts. It looks like you fixed the grainy/strange eye-effect issue already
Wetmaxiskirts said: Thanks for being willing to take a look. There's nothing skimpy or suggestive in my prompts which is why I get so frustrated. I've given up trying to use Bing, but the following prompt is an example of what's consistently blocked on Microsoft Designer Image Creator. Users are encouraged to be wordy, so I am!
[edited for brevity]
Any tips would be greatly appreciated, thanks!
[edited for brevity]
Any tips would be greatly appreciated, thanks!
I'm not sure if any of this will help, but these are things to try:
"beautiful" is generally redundant, as the majority of model photography that the generator was trained on are, well, models. A lot of times when I include "beautiful" in my prompts, I get rather ...voluptuous results. lol I think the AI associates "beautiful" with big boobs, and that could be triggering the sensors.
You may be overdoing it on the wet terms and synonyms. Some of those words ("wetness," and "wet skin" in particular) are used far more commonly in erotica and porn than in normal speech, and that may be triggering the sensors.
I often don't even use any form of wet/drenched/soaked descriptors, and instead rely on environmental effects to indirectly create the wet clothes and wet hair, (but the obviously drenched look has never really been that important to me either, so some descriptors are probably needed for that). "In heavy rain," "splashed by xxxx," or "after swimming" can often do the same thing as all of those references to wetness. Also, moptopumd gave some great advice for getting wet hair without actually saying "wet hair":
moptopumd said:
Sure thing. As an example:
close-up photo of a millennial female. coated in water. in a pool of water. in-ground pool. neck deep in water. splashing. water is dripping off the head and clothes. grey t-shirt, jeans, glasses, beautiful long blond hair smoothed sleek and flat, wet hair, wet clothes, summer day
So, first off, there is a bit of science to this, and a bit more luck. I was getting some amazing images with pretty much this exact same prompt two days ago. Yesterday it wasn't working so much. But Bing is like that from time to time.
Anyway, once you establish your model and background setting, you need to add a source of ongoing wetting. If you put the model in a pool of water, they will only be wet below the surface of the water. You need rain or something else to actively wet the upper half of your model. "Splashing" works to that effect. Sometimes it will act like somebody dumped a bucket of water on their head, other times it will just give a little ripple in the water and still soak the upper half of the model. You can also use rain to the same effect. The "coated in water" just kind of makes the splashing effect work. I have never gotten a model completely soaked without that prompt, but it also doesn't work alone. Like you have to have a good battery AND gas in your tank for your car to run. The prompts "wet hair" and "wet clothes" are not always needed, but give better results more frequently if they are there. The "hair smoothed sleek and flat" bit helps a lot too. Styled hair doesn't want to give the fresh out of the water look anywhere near as often. The "wet hair" prompt just makes hair slightly damp usually. The combined source of water, the dampness, and the hair being straight all combined give me the most soaking wet hair results. "Wet clothes" is another one that is kinda meh. I never notice it doing anything without the other prompts, but I believe it returns more good results than just the other prompts alone. Then you just figure out your posing and stuff. These are the tools in my belt that I use to get my results. That's the science. I would say it's still 50% or more luck just hoping Bing plays along with you at that time.
gazdadude said:
Can I ask how you do wet pictures
Can I ask how you do wet pictures
Sure thing. As an example:
close-up photo of a millennial female. coated in water. in a pool of water. in-ground pool. neck deep in water. splashing. water is dripping off the head and clothes. grey t-shirt, jeans, glasses, beautiful long blond hair smoothed sleek and flat, wet hair, wet clothes, summer day
So, first off, there is a bit of science to this, and a bit more luck. I was getting some amazing images with pretty much this exact same prompt two days ago. Yesterday it wasn't working so much. But Bing is like that from time to time.
Anyway, once you establish your model and background setting, you need to add a source of ongoing wetting. If you put the model in a pool of water, they will only be wet below the surface of the water. You need rain or something else to actively wet the upper half of your model. "Splashing" works to that effect. Sometimes it will act like somebody dumped a bucket of water on their head, other times it will just give a little ripple in the water and still soak the upper half of the model. You can also use rain to the same effect. The "coated in water" just kind of makes the splashing effect work. I have never gotten a model completely soaked without that prompt, but it also doesn't work alone. Like you have to have a good battery AND gas in your tank for your car to run. The prompts "wet hair" and "wet clothes" are not always needed, but give better results more frequently if they are there. The "hair smoothed sleek and flat" bit helps a lot too. Styled hair doesn't want to give the fresh out of the water look anywhere near as often. The "wet hair" prompt just makes hair slightly damp usually. The combined source of water, the dampness, and the hair being straight all combined give me the most soaking wet hair results. "Wet clothes" is another one that is kinda meh. I never notice it doing anything without the other prompts, but I believe it returns more good results than just the other prompts alone. Then you just figure out your posing and stuff. These are the tools in my belt that I use to get my results. That's the science. I would say it's still 50% or more luck just hoping Bing plays along with you at that time.
And a side question: Your Bing pictures pretty much all have a grainy look to them, with a strange effect on the eyes. Is that intentional? If not, I think that's caused by using "photo" as your image type keyword. I've found that "photographic image" gives clearer images and I have a lot less issues with the eyes.
Finally, I used both my advice and moptopumd's advice to rewrite your prompt to test it all out and got these as results. I didn't make too many attempts because I already use up all my boosts for today on making images for my latest D&D character idea: an orc warrior princess/barbarian wielding a greataxe while wearing a tattered, bloodstained ballgown. As much as I'd love to share some of those pictures, they're probably against the forum rules
This is the prompt I used in Bing Image Creator. The clothing isn't super shiny with rivulets of water, but I also didn't play around with the prompt too much. I just wanted to show it works and give you some idea of what it looks like. I used the prompt 3 times and got 4 images each time, so none were blocked at all. The hair looks realistically wet in all but one of the 12 images, and a few of the images were a little iffy on whether or not the clothes were actually wet. But still, 7 pretty decent wetlook images out of 12 is great odds. This was a quick attempt at a prompt, so with some playing around with it, you could get the full-body shot (putting shoes in the prompt sometimes works for that) with more obvious wetness. I know the patterns or details on the clothing often overrule the wet look, so leaving the floral part out might work better.
"full-length photographic image of a happy woman in a garden on a sunny day washing her hair under an outdoor shower wearing drop earrings and small pendant and 1970's-style wet long-sleeved collared dark navy floral blouse and wet flared turquoise silk floor-length skirt, coated in water, splashing, hair smoothed sleek and flat, full-body shot"
I hope some of this helps!
Edited to add: I just looked at some of your more recent image posts. It looks like you fixed the grainy/strange eye-effect issue already
Happy New Year to all! Sorry for such a slow reply, Kabe22 (I've been out of the loop here over the festive period). Having seen elsewhere that you've been feeling ill over the new year period, I hope you're improving now. Thank you so much for your thoughts and suggestions on what best to try to defeat the blocking algorithms. Interestingly, I found that Bing was happy the shorter prompt you suggested, but it was blocked on MDIC about 50% of the time and only generated 1 image per run otherwise. In my experience previously, the opposite was true and MDIC was the more chilled of the two.
Having had a break from it, I'm at a crossroads and have to decide whether or not to continue battling with the AI engines for what is, compared to much of what's being successfully generated and posted, pretty tame stuff. I suspected I'll end up continuing but with reduced frequency.
Regarding the grainy nature of my images, I can't say I'd noticed that and it definitely wasn't my intention. What I usually do (if I remember!) is to sharpen the images I've generated before I upload them, so perhaps that's doing it? I thought they looked better that way, but I could always be wrong!
Eyes are often an issue for me, but I don't recall having seen anyone else referring to it as being a problem for them. It's very disappointing to have an otherwise great-looking image but with the woman looking like an extra in Westworld! I don't know of a surefire solution to it yet and will probably be more strict with myself to exclude images where the eyes don't look sufficiently natural.
Anyway, here are some teasers (not sharpened!) from future selections, which were generated at a happier time when the MDIC blocking algorithms were more tolerant and, dare I say, fairer:
moptopumd said: I have never had much luck with Microsoft Designer. My prompts didn't work as well as on Bing, I didn't like getting only one image at a time, and I didn't like that there was no save function or even a history of creations, etc
Just to say that MDIC can save your creations - in fact it does automatically save every single one of them in the cloud storage associated with your account. What it doesn't do, unlike Bing, is retain the prompt that was used to generate the saved images, which is a bit poor really. Equally, few people would want every single image they've generated to be saved (at least until you run out of cloud storage).
Wetmaxiskirts said: Happy New Yera to all! Sorry for such a slow reply, Kabe22 (I've been out of the loop here over the festive period). Having seen elsewhere that you've been feeling ill over the new year period, I hope you're improving now. Thank you so much for your thoughts and suggestions on what best to try to defeat the blocking algorithms. Interestingly, I found that Bing was happy the shorter prompt you suggested, but it was blocked on MDIC about 50% of the time and only generated 1 image per run otherwise. In my experience previously, the opposite was true and MDIC was the more chilled of the two.
Having had a break from it, I'm at a crossroads and have to decide whether or not to continue battling with the AI engines for what is, compared to much of what's being successfully generated and posted, pretty tame stuff. I suspected I'll end up continuing but with reduced frequency.
Regarding the grainy nature of my images, I can't say I'd noticed that and it definitely wasn't my intention. What I usually do (if I remember!) is to sharpen the images I've generated before I upload them, so perhaps that's doing it? I thought they looked better that way, but I could always be wrong!
Eyes are often an issue for me, but I don't recall having seen anyone else referring to it as being a problem for them. It's very disappointing to have an otherwise great-looking image but with the woman looking like an extra in Westworld! I don't know of a surefire solution to it yet and will probably be more strict with myself to exclude images where the eyes don't look sufficiently natural.
Anyway, here are some teasers (not sharpened!) from future selections, which were generated at a happier time when the MDIC blocking algorithms were more tolerant and, dare I say, fairer:
Having had a break from it, I'm at a crossroads and have to decide whether or not to continue battling with the AI engines for what is, compared to much of what's being successfully generated and posted, pretty tame stuff. I suspected I'll end up continuing but with reduced frequency.
Regarding the grainy nature of my images, I can't say I'd noticed that and it definitely wasn't my intention. What I usually do (if I remember!) is to sharpen the images I've generated before I upload them, so perhaps that's doing it? I thought they looked better that way, but I could always be wrong!
Eyes are often an issue for me, but I don't recall having seen anyone else referring to it as being a problem for them. It's very disappointing to have an otherwise great-looking image but with the woman looking like an extra in Westworld! I don't know of a surefire solution to it yet and will probably be more strict with myself to exclude images where the eyes don't look sufficiently natural.
Anyway, here are some teasers (not sharpened!) from future selections, which were generated at a happier time when the MDIC blocking algorithms were more tolerant and, dare I say, fairer:
I didn't mean that as a criticism about the graininess or eyes. I was just curious because it was something I'd seen a lot from you but not much from anyone else recently. I'm sorry; I didn't mean for that question to discourage you from posting. It might just be that you were using an image generator I'm not used to seeing. I don't know. But I didn't mean to call you out over it or anything. I like the images you share!
One thing I've noticed with eyes from my own experience is that trying to force a strong emotion in an image (scared, sad, angry, etc) tends to get those sorts of effects when the mood of the rest of the image doesn't match. I've seen this from some of the humiliation-style images people post here: if the overall image is playful or there's laughing spectators but the central figure of the image is expressing an opposite emotion, the eyes for whatever reason end up with a dark outline. Sometimes it's accompanied by an exaggerated facial expression, but a lot of times, the eyes are the only thing that look off.
As far as differences between Bing and MDIC and what prompts they accept, I'm afraid that's beyond my knowledge. I got frustrated with MDIC the first time I used it because I was trying to make a (fake) pool party flyer and it just kept giving me the same handful of stock images with the text moved around. Not even AI generated stuff. Just literal stock images. I'm sure I stumbled into some setting I didn't intend to use, but I haven't tried again since.
And, as I learned from trying to generate images from other people's descriptions, Bing really does work better with shorter prompts. I was trying too hard to force specifics when, as Bobographer says, I just need to let the AI do the work and fill in between the lines.
Some unlucky participants in the corporate team-building exercise realise that perhaps they should have brought a change of clothes.
Kabe22 said:I didn't mean that as a criticism about the graininess or eyes. I was just curious because it was something I'd seen a lot from you but not much from anyone else recently. I'm sorry; I didn't mean for that question to discourage you from posting. It might just be that you were using an image generator I'm not used to seeing. I don't know. But I didn't mean to call you out over it or anything. I like the images you share!
One thing I've noticed with eyes from my own experience is that trying to force a strong emotion in an image (scared, sad, angry, etc) tends to get those sorts of effects when the mood of the rest of the image doesn't match. I've seen this from some of the humiliation-style images people post here: if the overall image is playful or there's laughing spectators but the central figure of the image is expressing an opposite emotion, the eyes for whatever reason end up with a dark outline. Sometimes it's accompanied by an exaggerated facial expression, but a lot of times, the eyes are the only thing that look off.
As far as differences between Bing and MDIC and what prompts they accept, I'm afraid that's beyond my knowledge. I got frustrated with MDIC the first time I used it because I was trying to make a (fake) pool party flyer and it just kept giving me the same handful of stock images with the text moved around. Not even AI generated stuff. Just literal stock images. I'm sure I stumbled into some setting I didn't intend to use, but I haven't tried again since.
And, as I learned from trying to generate images from other people's descriptions, Bing really does work better with shorter prompts. I was trying too hard to force specifics when, as Bobographer says, I just need to let the AI do the work and fill in between the lines.
One thing I've noticed with eyes from my own experience is that trying to force a strong emotion in an image (scared, sad, angry, etc) tends to get those sorts of effects when the mood of the rest of the image doesn't match. I've seen this from some of the humiliation-style images people post here: if the overall image is playful or there's laughing spectators but the central figure of the image is expressing an opposite emotion, the eyes for whatever reason end up with a dark outline. Sometimes it's accompanied by an exaggerated facial expression, but a lot of times, the eyes are the only thing that look off.
As far as differences between Bing and MDIC and what prompts they accept, I'm afraid that's beyond my knowledge. I got frustrated with MDIC the first time I used it because I was trying to make a (fake) pool party flyer and it just kept giving me the same handful of stock images with the text moved around. Not even AI generated stuff. Just literal stock images. I'm sure I stumbled into some setting I didn't intend to use, but I haven't tried again since.
And, as I learned from trying to generate images from other people's descriptions, Bing really does work better with shorter prompts. I was trying too hard to force specifics when, as Bobographer says, I just need to let the AI do the work and fill in between the lines.
My humblest apologies - something I phrased very badly has given you the wrong impression about what I was saying!
What I meant by "eyes are often an issue for me, but I don't recall having seen anyone else referring to it as being a problem for them" is that I haven't seen others who are generating AI images mentioning that they have issues with people in the images they're generating having unrealistic eyes - that robotic, glazed expression that the women in quite a few of my images have. I never for one moment meant to imply that you were being critical, so I'm sad that my clumsy phrasing made you feel that way. My review of what I'm doing is simply based on not having the time or inclination to keep wrestling with seemingly increasingly stringent algorithms when what I'm doing isn't really risqué in the grand scheme of things.
Waiting for a Blind Date
There are only two images, as Bing kept giving me dog after dog, enough to fill several kennels. So here's the story . . .
She had invited him over to her condo, and he insisted that he loved to play with food. She asked if he liked spaghetti and hinted that she'd be ready and waiting and he'd have a nice surprise when he came in the door.
But then after all the preparation and work, she got cold feet. Yes, she went through with her idea, but she needed to drink to take the edge off. Well, she took more than the edge off, as she may have had a few too many by the time he arrived.
If he were you, what would your first reaction be when you opened the door to her condo?
There are only two images, as Bing kept giving me dog after dog, enough to fill several kennels. So here's the story . . .
She had invited him over to her condo, and he insisted that he loved to play with food. She asked if he liked spaghetti and hinted that she'd be ready and waiting and he'd have a nice surprise when he came in the door.
But then after all the preparation and work, she got cold feet. Yes, she went through with her idea, but she needed to drink to take the edge off. Well, she took more than the edge off, as she may have had a few too many by the time he arrived.
If he were you, what would your first reaction be when you opened the door to her condo?
moptopumd said:
Those are lovely! Would you mind if I ask what prompt you use for the hair coverage? I have gotten some amazing and consistant results with a prompt or series of prompts, and then the next day that prompts will give me mediocre results or give me a prompt warning. A couple of days ago I got some absolutely awesome images with hair coverage, and then yesterday I burned through my daily limit on two accounts and the best I could get looked like a splat of green bird poo lol.
Those are lovely! Would you mind if I ask what prompt you use for the hair coverage? I have gotten some amazing and consistant results with a prompt or series of prompts, and then the next day that prompts will give me mediocre results or give me a prompt warning. A couple of days ago I got some absolutely awesome images with hair coverage, and then yesterday I burned through my daily limit on two accounts and the best I could get looked like a splat of green bird poo lol.
Hey thanks. To get the gungey hair it's taken quite a while of experimenting with very mixed results - some completely fluke too. Sadly I've not quite achieved the splat of green bird poo lol but equally it's either been watery or doesn't look real. In the end it's a case of emphasising the hair being totally gunged as well as thinking about what the wet hairstyle was in the first place - that seemed to help with the effect
What....there's no shampoo left??
Bobographer said: If he were you, what would your first reaction be when you opened the door to her condo?
"Damn! I forgot the grated cheese!"
I dream of being transformed into a fruit, or somthing like a glass of wine...
|
Love you, too |
|
Love you, too |
ninadunklin said:
Hey thanks. To get the gungey hair it's taken quite a while of experimenting with very mixed results - some completely fluke too. Sadly I've not quite achieved the splat of green bird poo lol but equally it's either been watery or doesn't look real. In the end it's a case of emphasising the hair being totally gunged as well as thinking about what the wet hairstyle was in the first place - that seemed to help with the effect
moptopumd said:
Those are lovely! Would you mind if I ask what prompt you use for the hair coverage? I have gotten some amazing and consistant results with a prompt or series of prompts, and then the next day that prompts will give me mediocre results or give me a prompt warning. A couple of days ago I got some absolutely awesome images with hair coverage, and then yesterday I burned through my daily limit on two accounts and the best I could get looked like a splat of green bird poo lol.
Those are lovely! Would you mind if I ask what prompt you use for the hair coverage? I have gotten some amazing and consistant results with a prompt or series of prompts, and then the next day that prompts will give me mediocre results or give me a prompt warning. A couple of days ago I got some absolutely awesome images with hair coverage, and then yesterday I burned through my daily limit on two accounts and the best I could get looked like a splat of green bird poo lol.
Hey thanks. To get the gungey hair it's taken quite a while of experimenting with very mixed results - some completely fluke too. Sadly I've not quite achieved the splat of green bird poo lol but equally it's either been watery or doesn't look real. In the end it's a case of emphasising the hair being totally gunged as well as thinking about what the wet hairstyle was in the first place - that seemed to help with the effect
That makes sense. It's weird, looking at everybody else's AI creations is what got me to try my hand at it as well. I have now generated thousands of images and lived the experience. Yet when I come here and look at everybody else's creations, I still take for granted all of the blocked prompts and bad prompts that everybody went through to get what we see, and never think about the fact that I'm only looking at a few hand picked images out of countless others created or attempted. And yeah, I have created some images that I find breathtaking, and I wouldn't be able to begin to tell you what I did to get them. Even when you write a good prompt that produces those wow results, it's still a combo of facial expression and setting and lighting and angle and luck etc....
A few messy ones:
And some for the wetlookers!
|
Love you, too |
Design & Code ©1998-2025 Loverbuns, LLC 18 U.S.C. 2257 Record-Keeping Requirements Compliance Statement
Epoch Billing Support Log In