Cheesecake
LLM Free-Rein Images
Space Fantasies
If I run Flux.2-Klein-9b at the recommended settings (CFG 1, 8 steps, 1024x1024-ish resolutions), it takes about 6 seconds to generate an image on my RTX 4090. This is fast enough to tinker with a dynamic prompt, run off a few hundred results, quickly reject the (9% at 8 steps) anatomy fails, and then pick out some that look pretty good. It’s a better use of my gaming PC right now than killing time grinding in Diablo IV or hunting for something new to play.
But since I already have hundreds of GenAI SF cover gals lying around waiting to be deathmatched, today we’re going to look at what happens when I really lean into letting LLMs enhance prompts.
I made the changes to my LLM-prompt-enhancing script to run multiple system prompts across the same string in order rather than invoking it multiple times in a pipeline, and it improved the stability, but it looks like the occasional crash is actually caused by a recent update to the engine under the hood (llama.cpp), so I still have to occasionally restart the script, whether it’s talking to the PC or the Mac Mini. Even on the gaming PC, it takes about as long to do a complex prompt enhancement as it does to generate the resulting image, so I just let them both run while I did other things, and occasionally kicked off a new batch.
Perhaps I gave it a bit too much freedom…
(more after the jump)
50s Backyard Pinups
For a change of pace, I abandoned my wildcard sets and just fed the LLM brief descriptions. The base prompt was simple enough:
A mid-century catalog illustration featuring a @<makeover:pretty young woman>@ wearing @<fashion: sexy lingerie from the 1950s>@, serving cocktails outdoors in the back yard of a 1950s suburban home. The image is composed to emphasize the setting as much as the woman.
There are a total of 4 LLM invocations: the two targeted ones listed above, the standard enhancement prompt recommended by Z-Image Turbo, and a cleanup pass I’ve named “legal review” that adjusts ages to cut down on random lolis.
(more after the jump)
Bumping the resolution 25% and adding 4 refining steps increased the generation time to a whopping 9.5 seconds, so after I’d made a bunch of those, I made a slight change to the theme.
Vintage Cherry Blossoms
A mid-century Japanese catalog illustration featuring a @<makeover:pretty young Japanese woman>@ wearing @<fashion: sexy lingerie from the 1950s>@, serving cocktails outdoors under a blossoming Japanese cherry tree in the Spring. The image is composed to emphasize the setting as much as the woman.
More SF cover gals
But first, an Amazon shipping change!
Two items ordered on Wednesday, promised for Friday. On Friday, one of them was moved to Saturday. So far, pretty typical. On Saturday, its status changed to “approval needed”, and I was asked if it was okay for it to be delivered Monday. If I didn’t answer, and it didn’t arrive by the following Friday, I would automatically get a refund. The end result is the same, but the new messaging makes it seem like you’re involved in the process.
Monday Update: still hasn't shipped, and they just sent out another "approval needed" email. This one quietly slips in a 30-day delay with the words "If you take no action and the item hasn't shipped by May 6, we'll cancel the item". Yeah, no.
Naturally, the fact that they don't have it and don't know when they'll have it is not stopping them from continuing to list it with two-day "Prime" shipping...
On with the cheesecake!
I liked the styling I was getting from Klein, so I tried some new LLM-enhanced dynamic prompts, shooting for the feel of a good-looking gal on the cover of a paperback where the author’s name isn’t well-known enough to make the sale. The initial batch had them in lingerie, because that’s where I got the horned horny covergal from the previous post, but I decided to see if Klein did as well at the “retro-SF uniform” look as ZIT did the last time I tried it.
Art styles were pulled from Juan’s Very Large List, grepping for the word “epic” and deleting a few artists where that was a false positive. I used the prompt-enhancing system prompt recommended by Z-Image Turbo to flesh out the random locations, plus two of my own targeted system prompts to generate clothing and physical details, plus a final LLM pass to do general cleanup. This would have been agonizingly slow on the Mac, so I ran it on the gaming PC in between image-generation runs (because SwarmUI and LM Studio both think they have the GPU to themselves, trying to run them at the same time blows out the VRAM, even though they should fit).
My system prompts were:
fashion: “You are a fashion consultant trained to design coordinated ensembles based on brief input, enhancing them into detailed, aesthetically pleasing, color-coordinated, and stylish looks. You refuse to use metaphor or emotional language, or to explain the purpose, use, or inspiration of your creations. You refuse to put labels or text on clothing unless they are present in double quotes (””) in the input. Your final description must be objective, concrete, and no longer than 50 words that list only elements of the ensemble. Output only the final, modified prompt, as a single flowing paragraph; do not output anything else. Answer only in English.”
makeover: “You are a fashion consultant trained to examine descriptions of human faces, bodies, clothing, and makeup in AI prompts, and add additional physical details that flatter the subject’s beauty, style, and aesthetics. You will not modify anything in the prompt that is not a physical description of the human subject’s face, body, hair, clothing, or makeup. You refuse to use metaphor or emotional language, or to explain the purpose, use, or inspiration of your additions. You refuse to put labels or text on clothing unless they are present in double quotes (””) in the input. Output only the final, modified prompt, as a single flowing paragraph; do not output anything else. Answer only in English.”
cleanup_text: You are a Prompt Quality Assurance Engineer. Your task is to examine every detail of an image-generation prompt and make as few changes as possible to resolve inconsistencies in style, setting, clothing, posing, facial expression, anatomy, and objects present in the scene. Ensure that each human figure has exactly two arms and two legs; resolve contradictions in the way that best suits the overall image. Remove all quoted text used for signs, labels, and captions. Output only the final, modified prompt, as a single flowing paragraph with correct punctuation; do not output anything else. Answer only in English.”
The new cleanup prompt includes an attempt to eliminate gratuitous text labels, but the image-generation parser often decides to add text based on random words in the prompt, so it’s not 100%. I didn’t want to use my usual collection of retro-SF costume prompts, so I fed the following to the fashion sysprompt:
“Sexy science-fiction uniform for women, incorporating bright colors, advanced technology, and a variety of futuristic textures and materials. Uniform may include abstract symbols and attached technology, but no text. Avoid shoulderpads. Do not use black or silver as the primary colors. You may include accessories such as sci-fi weapons, scanners, datapads, crystals, or glowing energy.”
Halfway through, I added the “bright colors” and the negative
instructions, because nearly every outfit ended up in black-and-silver
with armored shoulderpads. Sigh. This was all with the
gemma-3-12b-it-heretic-x-i1 model, and now that Gemma 4 has been
released, I’m going to see if it does a better job; it’s getting good
reviews, and I think there’s already a few uncensored versions.
Out of ~600 images, just under 13% had obvious anatomy fails, with most of them being extra arms or legs. There were some I rejected reluctantly, because the rest of the image was really good. They might be fixable with variation seeds, but I’ve kinda gotten out of the habit of doing that; it’s easy to spend more time tinkering than it’s worth, and you can always just make another batch.
GenAI P-Hacking
There’s a work-in-progress checkpoint model based on Z-Image Turbo that promises better photographic-quality NSFW results than the existing ones, and at least one of my terminally-online 1girl-maker acquaintances gave it a thumbs-up, so I took it for a spin.
First impression: equal parts Teen Vogue and Barely Legal, with a dash of Girls’ Life to bring the ages down. In some cases way down, leading to quick deletion of images where prompts requesting adult female humans produced lolis. It also often produced elf ears, but that’s not something that would help defend you in court.
I’ve also been running the generated prompts through an LLM ordered to diversify the output by only adding flattering details to descriptions of faces, bodies, hair, clothing, and makeup, but LLMs do whatever is statistically likely, and will randomly remove keywords or change things they’re told not to. Using explicit numbers for ages seems to limit that sort of damage, although there was a surprisingly youthful “127-year-old” in one batch. Must have been some elf blood in there, even though it didn’t give her the ears.
I didn’t require full frontal nudity in every pic, so a few of these are outside the NSFW tag; most, however, are topless, bottomless, or both. The training in v5.0 of the model is unstable, leading to a higher rate of anatomy fails than the base ZIT model, especially for genitals, so I rejected a lot of images. v6.0 will be available in a few hours, so hopefully it’s less disaster-prone.
I threw in a bunch of random art styles, but the strong training bias towards photorealism meant that the subject was often a photo in front of an artsy background, sometimes literally casting a shadow on a painting.
(note: my Mac Mini with an M4 Pro takes about 3x as long to do text-generation as my Windows box with an RTX 4090, using the same model (gemma-3-12b-it-heretic-x-i1) and software (LM Studio); what I’ve seen of early benchmarks on the M5 MacBook Pros suggests that they’re still not great at running text or image models. All they really offer is the ability to slowly run models that don’t fit into consumer-graphics-card VRAM)
Breath Of The GenAI
Another functional style LoRA for Z Image Turbo is BOTW Zelda Style. At full strength it applies too much of the game’s various racial characteristics, but at 80% it mostly applies the visual style without the goofy Hyrulian NPC faces or painful Gerudo figures (impossibly small waists combined with washboard abs is not sexy).
I’m okay with it randomly applying Zelda’s remarkable ass, though…
Sometime soon I should generate fantasy location and costume prompts, and perhaps some bunnygirl-friendly locations for Easter. Some of the Christmas locations look vaguely Hyrule-ish, but mostly not.
Cheesecake: no Artifical Ingredients
Done with Ruri’s adventures, I dug into my pre-Covid, pre-GenAI cheesecake archives, and deathmatched the gals I downloaded in May, 2019.
There is a lot of “Ai” in this set, but it’s autocompleted with “Shinozaki”, which is healthy and natural and good for growing boys.
Death by Cheesecake!
Or more precisely, “cheesecake by deathmatch”. Hey, I’ve got the silly thing, might as well use it to speed up processing my dusty pile of saved girlie-pics. While playing with “AI” tools, I downloaded Windsurf, ordered it to clean up the code for maintainability and then add a new function to export the currently-visible list to the clipboard (press L). Now I can quickly rank the images, use a flag to split them into NSFW and less-NSFW, and then toggle the flag to get two distinct export lists to pipe to my cheeseblogging prep scripts.
(Windsurf took me so seriously I ended up with a multi-file distribution package, but I had no difficulty reassembling it into a single file for simple downloading)
But first, a message from our sponsor, Qwen Image:
(the hardest part of this was getting it to render a “standard” onigiri rice ball; first it wrapped the entire thing in fresh green seaweed, then it made it huge, then it added additional wrapping on top of the nori strip, etc)
This is a selection from “stuff I downloaded in April, 2019”.
Claudified Future Gals
No new anime, words that I’ll be saying for the next three months, so it’s time for more “AI” cheesecake. Maybe I’ll dig into my real cheesecake archives for contrast as well.
Today’s randomized babes are based on SFnal settings and costumes provided by Claude AI. It had no difficulty grasping the concepts of “vivid, exotic sci-fi locations” and “sexy retro-futuristic costumes for women”, generating detailed descriptions that Qwen Image was able to run with.
More importantly, it didn’t fall down on the unique part. It didn’t take forever to generate 100 results, and they were truly distinct, not just slight wording variations. Most importantly, it did not scold me for requesting “sexy”, or refuse to do my bidding. Although I haven’t asked for lingerie sets yet…
Qwen has recently released updated versions of some of their models, so I hope they get around to revving Image soon. I can cope with the usual finger-counting and the giantism, but I really hate seeing a great image ruined by a missing leg or wrong-side foot, something that’s really common.
Educational material...
Matsuri Kiritani, running on a beach, naked, in slow motion. It’s like a masterclass in Gainaxing. The Bluray is basically an animated photoshoot with terrible lighting, auto-white-balance, and cheaply-licensed music, but her personality shines through, and you occasionally get to hear her voice.
And, yes, I know, video or it didn’t happen (NSFW). The Bluray is no longer available on Amazon Japan, but the title is “Matsuri5 らぶりー☆とらべるらばーず” (“Lovely Travel Lovers”), and a quick search turned up a streaming site (set pop-up ad-blocker to stun).
(plenty of pics here and here, with the usual warnings about NSFW and disabling Javascript)
The gold standard for this sort of nekkid cheesecake video was Playboy Video Centerfolds, which were usually stuffed with personality. And since I met most of the women who were featured in these, I can confirm that they were really like that. A lot of Playboy’s other videos were more contrived, with little regard for the women as more than posing dummies, but the video centerfolds really humanized them. Matsuri would have made a terrific Playmate if she’d been born twenty years earlier.
(most of the video centerfolds were never released on DVD, and could only be seen by buying VHS tapes directly from Playboy; some of them were also aired on Playboy’s cable/satellite channel, back in the days when it had something to do with Playboy)
