Design a photorealistic, awkward-looking adult character with a distinctive outfit and deadpan manner, then define a repeatable posting format built around one action in new everyday places. Useful for creating an unusual AI influencer or recurring character concept.
Makes cringe, deadpan, odd-looking AI characters people argue about, on varg: a photoreal, bizarre-but-believable person (strange haircut, wrong suit, absurd shoes) who takes himself completely seriously and repeats one action in a new place every post: the "Jean Phil" format of late 2026. Builds the character sheet and the posting format. Use when someone asks for a weird, cringe, odd, awkward or deadpan character, a strange AI influencer, a "is he real?" persona, or a character like Jean Phil. Part of varg-character-design (definition, sheet, reuse in video).
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
The late-2026 meta. Jean Phil (blonde bob, curled moustache, brown houndstooth suit, shadowboxing around Paris) reached 244K Instagram followers from 12 posts, one clip at 35.9M views; Bill Smith (burgundy suit, platinum bangs) 18.3M on one clip. They work because they are bizarre but believable: people scroll past 90 real humans to argue in the comments whether this one is real, and that argument is the distribution.
Sheet, crops and video: varg-character-design.
Definition: a real-looking adult (35–65) + a look that is slightly wrong everywhere + one repeated action, done with total seriousness.
Details (the face must look like a real person, not a cartoon):
Clothing: one silhouette readable in one frame.
| Character | Prompt seed |
|---|---|
| Gérard (tested) | 61-year-old Belgian man, extremely tall and lanky: very long thin legs, arms that hang to mid-thigh, narrow sloping shoulders, a long thin neck with a prominent Adam's apple, a small head for his height; thin ginger comb-over, huge tinted aviator glasses, droopy ginger moustache, completely serious; mustard-yellow corduroy three-piece suit with trousers slightly too short showing white socks, brown knitted tie, white quad roller skates with orange wheels |
| Dieter | 52-year-old German accountant, short and wide, blonde bowl cut, thin rimless glasses, a pencil moustache; a mint-green polyester leisure suit, a fanny pack, socks with sandals; power-walks everywhere with a stopwatch |
| Rex | 44-year-old Australian, wiry, a sun-bleached mullet with a perm, a gold chain, wraparound sunglasses on top of his head; a burgundy velvet tracksuit, unbranded, white cowboy boots; slow-motion karate kata in public places |
Gérard: sheet (Seedream 5 Pro, 7 credits).
The model sheet from varg-character-design, model seedream_5_pro. Tested: height is invisible on a plain sheet even with proportions; Gérard reads as "tall" only in a scene with something to compare (a doorway, a car roof, a normal-height person). Put the scale in the scene prompts.
minimax_h3_max_recast with one clean full-body photo of him.No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan worthwhile local tasks by checking dependencies, effects, resources, and platform boundaries, then execute the exact approved plan. It can use safe parallel work or suitable Apple-silicon backends when the project exposes them.
Turn a winning TikTok or Meta ad into a structured creative test plan. Identify what made it work, plan distinct concepts, set test budgets and review timing, and use funnel metrics to decide whether to stop, iterate, or scale each ad.
Record deferred engineering decisions and temporary workarounds in a debt registry, with context such as effort, ongoing cost, affected area, and payoff trigger. Entries receive short labels so they can be reviewed or dropped later.
Generate or compare AI agent code for LangChain, EINO, AutoGen, AgentScope, and CrewAI using framework-specific templates, API mappings, conventions, and project structures. Reference files include verification dates to help identify potentially outdated guidance.
Investigate a reproducible bug, test failure, or unexpected page behavior, then make a narrowly scoped fix. The workflow calls for a regression test before changing code, verifies the fix, and reports remaining risks and evidence while avoiding unrelated refactoring or feature work.
Build an AI agent project through six collaborative stages, from requirements and architecture to tools, prompts, code generation, and verification. Start framework-independent, then generate a runnable project for frameworks such as LangChain, EINO, AutoGen, AgentScope, or CrewAI.