Fake (@FakeUGC) header
Fake (@FakeUGC) profile picture

scaling ai models | https://teapaw.org/t.co/jdpW90wPWQ

Joined March 2022
your ai model looks too PERFECT and every guy scrolls past her.. she reads as a render. no guy pictures her ever talking to him a guy has no fantasy to step into with a girl who looks like that so you build her so she doesn't read as a render > generate 20 or more images of your ai model for one shot. throw most of them out, about 80% > look at each one that's left for about 2 seconds and ask one thing. does she read as a real girl or as a render > bin the renders even when nothing is wrong with them. a face with nothing wrong reads as generated that 2 seconds is the same window a guy gives you on his feed keep the one a guy would believe comment "RENDER" and i'll send you the quick version of how i build my ai model
3
16
1,817
this is probably the lowest effort content that still does numbers the less restricted cloud models like seedream keep messing up your ai model's face because they're just not as strong as the top ones and you're sitting there tweaking it cover her face with the phone mirror selfie done nothing left to get wrong. and a girl holding her phone over her face in a mirror reads more real anyway it's piss easy to prompt. anyone can do it then the same still goes straight into wan or any image-to-video model ask for almost no movement. no posing no zoom now you've got a clip too
2
9
1,063
ONE image is all it takes to keep your ai model consistent every single time the tool doesn't remember her from last time. so every new picture or video it makes of her starts from scratch one board of her goes in every time > her face straight on close up > her face at three-quarter > full body from the front > full body from the back only the angle changes between the four. the body matters as much as the face you hand it that board each time so it has her whole look to pull from instead of inventing her BEST way to keep her consistent here's an example
6
13
269
14,496
here's another output from the exact same workflow this sh*t is fucking insane comment "REAL" and i'll send you the full system to make these
i had to check twice that this was my ai model seedance 2.5 nailed every part that gives most ai clips away the shaky front camera at arm's length, her looking up and away mid sentence, a guy answering from off camera, street light flaring the lens at night it's starting to look like a real creator filmed it my workflow one-shot it. Genuinely terrifying.
7
2
18
2,068
i had to check twice that this was my ai model seedance 2.5 nailed every part that gives most ai clips away the shaky front camera at arm's length, her looking up and away mid sentence, a guy answering from off camera, street light flaring the lens at night it's starting to look like a real creator filmed it my workflow one-shot it. Genuinely terrifying.
31
68
4
1,666
233,140
my airtable workflow is f*cking INSANE.. it's spitting out images and clips of my ai model that look like real life i find a format that already went viral on another page and recast her into it. every idea comes back as 10 versions and i only post the best one and her face comes from her saved reference images, so it's the same girl in every single post comment "AIRTABLE" and i'll send you the full system to make these
3
16
2,395
i stopped generating photos of my ai model and started screenshotting her out of videos every image model smooths the skin, evens the light and kills the small flaws that make a girl look real so i build her start frames inside seedance 2.5 now her locked dataset reference goes into a 4 second vertical clip at 1080p. i let it run, scrub through and pause where she looks most like a phone caught her that one frame becomes the start image for the whole reel it costs more per still than running an image model. but the face comes out of her dataset so it matches every other post on the page pull one start frame tonight and put it next to your last image model still. if the face doesn't match her dataset, run it again here's an example of an output
8
7
162
14,560
i just steal every single piece of viral content i see and drop my ai model into it the best way to go viral is copying something that already did. the video proved itself before i generate anything, so i never need an idea of my own and i copy the timing, not just the idea. every line and every movement lands on the same second as the original pov, a guy walks up to her car and asks her for directions then i drop the original reel into claude and ask it to analyse why it works and give me a list of similar formats to recast her into once one lands, i run three more versions of that same format the same week and keep rinsing it comment "RECREATE" and i'll send you the full system to make these
3
2
18
3,078
a girl in a rashguard on the mats stops a guy cold the content on every ofm page is pretty much the same, so the hobby she's wrapped in is what makes him follow skip hobbies where real girls already post. yoga, pilates, regular gym. they own those feeds and the algorithm already picks them first pick a hobby where women don't show up. the ones i'd run right now: - combat sports - fishing and hunting - motorsport, f1, sim racing, drifting - powerlifting and strongman post 3 reels a day in the same hobby and send every reel to fanvue before you generate a single image write down four things: her outfit, her setting, her caption topic, which men it pulls if you can't fill all four from one hobby pick a different one
1
1
12
9,665
people are PRINTING on reels with fake omegle calls right now a girl on omegle, a guy sees her face and loses it. this exact one got 38 million views and 504K likes it's one of the lowest effort formats you can make. only her half gets generated, the guy is a reaction clip from another video edited in 1. screenshot the girl from an omegle reaction clip that's already working 2. ask claude for a prompt that matches her look with your ai model in it 3. paste that prompt into nano banana with your ai model's image for the face and the screenshot so it copies the vibe of the shot 4. animate her in veo 3.1, then stack her under the reaction clip in capcut so it looks like an omegle call pick a reaction clip that's still picking up views and run these steps on it tonight
2
1
16
15,272
this is easily the easiest viral format for ai model content on reels right now... a stranger stops a girl on the street and asks about her outfit the mistake is prompting it like a shoot. clean camera, her talking straight to the lens, a perfect line. that's what makes it look staged a real one gets filmed by some random guy on his phone it shakes, it blurs, she walks out of frame and cuts him off mid question so that's what goes in the prompt: - handheld, whip-pan away, motion blur, she walks out of frame - every beat timestamped in whole seconds, 0-3s, 3-6s - her lines in { } with the language and accent named first - the question in brackets as an off-camera voice keep your ai model and the format the same every episode and only change the outfit
2
2
24
5,735
i haven't had a single original idea for my ai model in months.. every reel on her page started as somebody else's reel i only pull from 12 accounts whose reels already get views. if the format works for them it works for me the pick is always a real girl. never an ai page. an ai reel moves like nothing alive and that carries straight into yours i look for a clip where people are still reacting and no other page has used the format yet if every page already runs it i move on a real clip carries rhythm and movement a prompt can't describe. the way she shifts her weight, how her head moves while she talks the whole pick takes about 10 minutes. then the reel gets recreated with my model in it open one account from your follow list tonight and find one reel that's still picking up. if nobody else has run it yet it's yours
4
3
25
3,237
the voice is the one thing that still gives ai video away and i just KILLED it. when your ai model's voice is made separately from the video, it sits on top of the scene. sounds like someone pasted it in the fix was writing the sound into the same prompt as the video. her line, the footsteps, the fence rattling when she backs him into it now her voice gets louder when she's inches from the lens and quieter a few feet back. the room stays quiet underneath, just open air and distant traffic i ran the audio through gemini and it read it as an authentic phone recording. every sound in it came back as real rewatch your last clip. if her voice sounds the same at every distance, write the sounds into the prompt instead of adding them after
1
2
793
i built a chrome extension that reverse engineers any picture or reel. right-click it on instagram, tiktok or pinterest. a few seconds later you get the prompt to recreate it with your ai model. - pics → image prompt for nano banana, seedream or gpt image - reels → the shot, dialogue, sound, outfit and the turn, second by second, plus a video prompt for seedance or kling no subscription. it runs on a free gemini key. comment "REVERSE" and i'll send you the extension (must be following + RT)
11
5
9
806
i never sit down wondering what to post.. when one of my ai model's reels does well i write down three things. the scenario, the framing and the length one of mine is her in the driver seat, same angle every reel. the only thing that changes is the question those three lines go into claude and i ask for 100 topics in the same format my page posts 3 a day, so 100 topics is 33 days of content from one winner to find the winner, check each reel at the 3-hour mark and again at 24 hours. if it gets double your usual views, lock that format before you write the 100, test two versions of it that change one thing each, just the question or just the length take your best reel tonight, write its scenario, framing and length in three lines and ask claude for 100 topics in that format
1
7
4,189
post a bikini photo in your first few weeks and watch instagram take your whole page down. it doesn't even have to be nsfw. an ai model page can get flagged for a bikini alone and the whole page gets pulled so nothing suggestive goes up until day 21. lip syncs, a coffee run, normal stuff only the "link me" in your bio makes it worse. people click it, see you've got fanvue linked, and report the page move the link out of your bio and put it inside a story highlight. that's how you get around it if the page goes down it's a new sim and day one again, so set the backup account up on a burner phone now before you need it
2
10
808
f*ck it.. here's the exact structure i break every viral reel into before i remake it: give gemini any clip with this prompt: "describe the video frame by frame, scene by scene, with an accurate description of the story and what happened" the breakdown only works if every timestamped block fills the same fields: 1. the shot. camera move and distance, "wide POV, eye level, handheld walk" 2. performance. body language and energy, "sits still" 3. dialogue with delivery. the stammer written out word for word 4. sound. the specific noise in that block, footsteps then the loud metal crash of the chain-link fence 5. her look. repeat it every block, black graphic top, ripped black tights, grey furry boots, silver pendant 6. find the turn. gemini names the exact second the story flips, 0:08 she stands and backs him into the fence gemini writes a video prompt at the end with [MY MODEL] as a placeholder push that prompt into seedance with your ai model as the reference, or a scene board of her you made in chatgpt. keep the turn beat where it is
1
1
8
825