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)

more...

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…

NSFW

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.

more...

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.

more...

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”.

more...

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.

more...

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)

I was dinking around with dynamic prompts for Stable Diffusion again, and at one point ended up getting a robotic catgirl. This seemed like a fine idea, so I stripped it down to the basics and tried to build back up into a specific look. I was getting reasonably consistent results with one model, but it was weak on backgrounds. TL/DR, I ended up running the same prompt and seed through 64 models because I wasn’t able to get all the elements at the same time: clearly robotic body, metal skin and face, metal cat ears and tail, pretty face, sexy figure, naughty bits covered, interesting background, requested pose.

So I ran the exact same prompt and seed through 64 models:

4k, crisp, high budget, highly detailed, intricate, ultra textured.
photorealistic, hyper realistic, ((robot girl)) at ((Towering spires
of glass piercing a sea of swirling mist)). ((robot face)), ((silver
metal skin)), ((silver metal face)), ((metal hair)), tiny breasts,
silver metal cat tail, black metal cat ears, full body, teen height,
teen face, teen body, wearing ((black metal corset bodysuit)), ((black
metal stockings)), ((black metal long gloves)), ((black metal collar))
with ((glowing crystal bell)). Cross-legged on floor, hands on knees,
upright posture, calm and collected with a cheerful expression.

I tried to bias it toward a slender look with “teen face/body/height” and “tiny breasts” (which generally produces B-C instead of D-H). I moved the location to the beginning because I kept getting just floors and solid-color backgrounds with the occasional generic room interior. Repeating the colors for each item helps to keep them from bleeding into other elements, but, as usual, doesn’t always work.

Anything XL

Definitely a catgirl, mostly-correct costuming, matte silver skin except for neck and eyes, plausibly robotic arms and legs, terrible tail (fur, broken), robot cat-ears, cute face, sleek little body, appealing pose but doesn’t match the prompt, nice background that matches prompt.

more...

Fun fact: the prompt elements “Christmas” and “Santa Hat” have a powerful impact on the setting (strong bias toward indoors, decorated Christmas tree, boxed presents, fireplace with stockings hung), clothing colors (bright red and bright green), and skin tones (white Euro/American). I had to completely rebalance my skin-color wildcard file and add emphasis and throw in an extra “dark” and move it to the front of the prompt before even mentioning the girl.

And, no, I wasn’t going to add prompts that pulled in the bullshit derivative marxist mid-winter “harvest” festival invented by a convicted torturer as a “black christmas”. Because I really don’t want to find out what directions that would push the engine.

Anyway, the only other big change compared to the last gallery is that the naughty bits are covered. This required some emphasized additions to the negative prompt, and a fair amount of pruning.

(I used my usual “5-star deathmatch” method of repeatedly downranking 2/3 of the images until only 1/81 end up with 5 stars. I was able to do this quite quickly because it wasn’t like my vacations to Japan where I only have so many source images; at five seconds a pop to make more, I can be quite aggressive at discarding them in DarkTable)

Y’know the best part of generating cheesecake with “AI”? You can order it not to use a fucking wide-angle lens!

more...