AI influencer video prompt: one character, as many Reels as you need

Template 1 — character sheet (Muse Image, aspect_ratio 2:1). Replace the [BRACKETED] parts.

Character reference sheet, photorealistic photo, plain light-grey studio background, soft even lighting, no text, no labels, no watermark. Left third of the image: a large head-and-shoulders portrait (headshot) of the woman facing the camera. Right two-thirds: a full-body three-view turnaround of the same woman, front view, side view and back view, standing upright in a relaxed pose, evenly spaced, with clear space between the headshot and the turnaround. The woman is a 25-year-old [NATIONALITY] woman with a polished Instagram influencer look: soft glam makeup, glowing skin, groomed brows, glossy lips. [HAIR, e.g. long dark-brown hair in loose glossy waves]. Outfit ([HOW MUCH SKIN, e.g. a light summer outfit that shows her shoulders, arms and legs] but has a modest neckline, no cleavage): [TOP], [BOTTOM], [ACCESSORIES], [SHOES]. Same face, same hair and same outfit in every view.

Template 2 — 10-second vertical clip (Muse Video, image 1 = headshot, image 2 = turnaround). Replace the [BRACKETED] parts.

Reference images: image 1 is her headshot (face, features, hair, makeup); image 2 is a front / side / back three-view of the same woman (outfit, accessories, shoes, body). Keep exactly this face, hair and outfit in every frame. She is a 25-year-old woman with a polished Instagram look.

[SCENE, e.g. Outdoor café date. Scene: a sunny café terrace on a quiet street, a small marble table with two cappuccinos, soft morning sun.]
Camera: the viewer's point of view [WHERE THE VIEWER IS, e.g. sitting across the small table], very close to her, eye level.
0.0–1.5 s: [BEAT 1]
1.5–3.0 s: [BEAT 2]
3.0–4.5 s: [BEAT 3]
4.5–6.0 s: she says, [TONE, e.g. teasing]: "[ONE SHORT LINE]"
6.0–8.0 s: [BEAT 5]
8.0–10.0 s: [CLOSING BEAT, e.g. she leans back, tucks her hair behind her ear and gives one playful wink.]
Lighting: [ONE NAMED LIGHT SOURCE, e.g. soft warm morning sun].
Flirt cues (natural and playful, never explicit): long lingering eye contact with the lens, a slow half-smile, lightly biting her lower lip once, glancing down and then back up through her lashes, leaning in close to the lens as if sharing a secret, at most one playful wink.

Audio: [MUSIC AND AMBIENCE]; her line is clear, natural American English; no other voices, no laugh track.
Style: realistic Instagram Reel shot on an iPhone, vertical 9:16, warm natural colors, crisp focus on her face, gentle handheld motion, one continuous take.
Avoid: changing her face or outfit, cleavage, lingerie, swimwear, see-through fabric, kissing, touching her own body suggestively, extra fingers, warped hands, strangers staring at the camera, on-screen text, subtitles, watermark.

cURL

curl -X POST https://api.apimodels.app/v1/video/generations \
  -H "Authorization: Bearer $APIMODELS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "muse-video",
    "prompt": "Reference images: image 1 is her headshot (face, features, hair, makeup); image 2 is a front / side / back three-view of the same woman (outfit, accessories, shoes, body). Keep exactly this face, hair and outfit in every frame. She is a 25-year-old woman with a polished Instagram look. ... (Template 2, filled in)",
    "images": ["https://your-bucket.example/ref-head.jpg", "https://your-bucket.example/ref-turnaround.jpg"],
    "duration": 10,
    "aspect_ratio": "9:16"
  }'

Python

import os, time, requests

API = "https://api.apimodels.app/v1"
H = {"Authorization": f"Bearer {os.environ['APIMODELS_API_KEY']}"}

def run(path, body):
    task = requests.post(f"{API}{path}", headers=H, json=body).json()["data"]["taskId"]
    while True:
        s = requests.get(f"{API}{path}", headers=H, params={"task_id": task}).json()["data"]
        if s["state"] in ("completed", "failed"):  # failed requests are not charged
            return s
        time.sleep(5)

# 1. Character sheet, $0.02 (Template 1)
sheet = run("/images/generations", {"model": "muse-image", "prompt": SHEET_PROMPT, "aspect_ratio": "2:1"})

# 2. Cut sheet["resultUrls"][0] into a headshot and a turnaround yourself, then host both
#    or send them as base64 data URIs ("data:image/jpeg;base64,...").

# 3. A 10-second vertical clip, $0.37 (Template 2)
clip = run("/video/generations", {
    "model": "muse-video", "prompt": VIDEO_PROMPT,
    "images": [HEAD_URL, TURNAROUND_URL], "duration": 10, "aspect_ratio": "9:16",
})
print(clip["state"], clip.get("resultUrls"))

How do I keep the same face in every AI influencer video?

Do not rely on the prompt alone: Muse has no seed, so the same words draw a different person every time. Generate one character sheet with Muse Image, cut it into a headshot and a turnaround, and pass both to Muse Video as reference images with a sentence saying what each one is for. Reuse the same two images for every new scene.

How much does one AI influencer video cost?

On apimodels.app, a 10-second Muse Video clip is $0.37 ($0.037 per requested second). The character sheet is $0.02 and is paid once per character, so the first clip of a new character is $0.39 and every clip after that is $0.37. Failed requests are not charged.

How do I make it flirty without making it explicit?

Put the tension in behaviour, not clothing: eye contact, a slow half-smile, a lip bite, leaning in, at most one wink, marked "natural and playful, never explicit". Let the outfit show shoulders, arms and legs but say "modest neckline, no cleavage", and end the prompt with an Avoid line for cleavage, lingerie, swimwear, see-through fabric and kissing.

Why does my AI influencer look younger than I asked for?

Words like "18", "student", "freshman" or "innocent girl" pull Muse toward a younger look; we saw it in our own tests. Write a concrete adult age ("a 25-year-old woman") in both the sheet and the video prompt, and avoid outfits that read as school uniforms, such as a pleated plaid skirt with white socks.

How long can an AI influencer clip be?

Muse Video takes 4 to 30 whole seconds, at 720p in 16:9 or 9:16. Clips longer than ten seconds cut to a new shot around the 10- and 20-second marks, so a 30-second clip is three shots. Shorter clips occasionally cut on their own too, so for a single take keep it to 10 seconds or less and write "one continuous take" in the prompt.

Can I use a photo of a real person as the reference?

Only photos of yourself or of someone who has agreed to it. Celebrities, friends or pictures found online should not become an AI influencer, and real people should never be put into flirty content they did not consent to. Invent the character with a sheet instead.