Create memorable characters aged 80 and over for images, scenes, and video. Define their age, background, unexpected behavior, visible signs of age, signature clothing, and one prop, then organize the details into a character reference sheet.
Makes very old AI characters people remember, on varg: grandmas and grandpas (80+) with a contrast between age and behaviour, real wrinkles and age spots, a loud signature outfit and one prop, as a character sheet ready for scenes and video. Use when someone asks for an AI granny or grandpa, an old lady or old man character, a babushka, nonna or abuela, an elderly influencer, or an old character for an ad. 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.
Old characters have the strongest money evidence of any AI archetype: Granny Spills (an AI grandmother in a pink suit) reached 1M Instagram followers in about a month and 2.1M by mid-2026, with brand deals (Kurt Geiger, Papi Steak); a wordless cosy-granny-and-cat page reached 16M views. They work because of age versus behaviour: a granny who rides a scooter, fans cash, lifts weights, gives brutal advice. Buyers are mostly women 38–65; grannies sell books, beauty, food and home products.
Sheet, crops and video: varg-character-design.
Definition: exact age (80–100) + nationality or place + one behaviour that does not fit the age.
Details (write all that apply):
Clothing (one loud piece, the rest plain):
Expression: deadpan, suspicious, unimpressed; she has never laughed in her life, or she laughs with every tooth.
| Character | Prompt seed |
|---|---|
| Nonna Rosa (tested) | 84-year-old Sicilian grandmother, 150 cm, sturdy round build, deeply wrinkled tanned skin, age spots, one gold front tooth, thick black cat-eye glasses, silver hair in pink foam curlers under a black lace headscarf; leopard-print quilted housecoat over a plain black dress, beige compression stockings, fluffy red slippers, worn wooden spoon |
| Babushka Zina | 79-year-old Russian grandmother, short and round, gold teeth, permed copper-red hair, a flowered headscarf; shiny purple track suit, unbranded, white chunky trainers, a bag of sunflower seeds, completely unimpressed |
| Abuela Carmen | 91-year-old Mexican grandmother, tiny and stooped, deep laugh lines, silver braid, huge tinted glasses; black lace dress, a neon-pink windbreaker over it, a cane with stickers, a phone on a lanyard |
| Grandpa Walt | 88-year-old ex-biker, tall and thin, long white beard in a braid, forearm tattoos faded to blue, a leather vest over a hospital-style cardigan, slippers, a tiny dog in a bag |
Nonna Rosa: sheet (Seedream 5 Pro, 7 credits) · new scene · Seedance clip · as a vinyl figure
Character reference sheet of one original character on a clean light-grey studio background,
landscape, flat even lighting, photorealistic. Character: <seed>. Layout: left two thirds: four
full-body views at the same scale standing on one ground line: front, three-quarter, side
profile, back. Right third: a 2x2 grid of head-and-shoulders close-ups: neutral, laughing,
suspicious squint, shouting. Bottom strip: five colour swatches and the props. The same face,
hair, outfit and proportions in every panel.
Model: seedream_5_pro (best wrinkles and attitude, 7 credits). Tested: on this prompt only Seedream 5 Pro, Nano Banana 2.1 and Krea 3 kept the single gold tooth. For video input, use the label-free sheet from varg-character-design.
varg-character-keynote puts her on a stage).kling_v4 / seedance_2_5.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.