AI 网红视频,是一个虚构的写实人物拍的竖屏短视频,每一条里她的脸、发型和风格都要一样。做这种视频的提示词其实是两段:一段角色设定图提示词,决定「她是谁」;一段按秒写的视频提示词,决定「她接下来十秒做什么」。本页把两段都做成了可直接复制的模板,用的是 Meta 的 Muse Image 和 Muse Video,并附上 4 个我们用它们做出来的案例。
Muse Image 是 Meta 的图像模型,Muse Video 是 Meta 的视频模型。在 apimodels.app 上它们叫 muse-image(每张 $0.02)和 muse-video(按请求秒数每秒 $0.037,720p,4 到 30 秒,横屏或竖屏,最多 4 张参考图)。两个模型都不保证每次都成功,Muse Video 也做不了超过 10 秒左右的一镜到底,下文会把这些限制一条条写清楚。
1. 用 Muse Image 出一张设定图。 要一张 2:1 的图:左边三分之一是大头照,右边是同一个人的正面、侧面、背面三视图,浅灰纯色背景,不要任何文字。一张图、一个人、视频需要的每个角度都在里面。它不拿来发,它就是「选角」。
2. 裁成两张参考图。 大头照管脸、发型和妆容,三视图管衣服、鞋和身材。我们的设定图里,两部分的分界在宽度的 39% 到 44% 之间,每张都不一样,所以要看着图裁,别按固定比例一刀切。
3. 两张一起交给 Muse Video,按秒写分镜。 先说清每张图管什么,再重复一次年龄,然后像分镜表一样写:场景、镜头、每 1.5 秒一个动作、一句台词、光线、声音、最后一行 Avoid。同一个人换场景,只需要换视频提示词,设定图可以一直用。
「ins 风真实感」不是一张完美的脸,而是看起来像朋友用手机随手拍的。提示词里有四样东西起了大部分作用。
写成具体数字的成年年龄。 「a 25-year-old woman」。我们实测时发现,「18 岁」「学生」「新生」「清纯少女」这类词会让 Muse 把人画得明显偏小,所以本页所有人物一律写 25 岁。
皮肤要像皮肤。 柔和精致妆、水光唇之外,雀斑、细小纹理、几缕碎发反而是真实感的来源。完美无瑕看起来就是渲染图。
写清楚是哪一种光。 窗边早晨的柔光、日落时的低角度光、暖色台灯。只写「好看的光」,出来的就是影棚。
写出拍摄设备。 「Realistic Instagram Reel shot on an iPhone, vertical 9:16, gentle handheld motion」。这一句决定了画面是网红手机视频还是广告片。
纯欲风的核心是「外表干净清爽,氛围带一点暧昧」。暧昧感要从表情和动作里来,并且把边界直接写进提示词,别让模型去猜。
衣服: 可以露肩、露手臂和腿(一字肩针织衫、无袖上衣、牛仔短裙),同时在设定图提示词里明确写「modest neckline, no cleavage」。
暧昧动作(flirt cues): 长时间看着镜头、慢慢浮现的半笑、轻咬一下下唇、低头再抬眼、凑近镜头像要说悄悄话、最多眨一次眼,结尾写「natural and playful, never explicit」。
Avoid 禁止清单: cleavage、lingerie、swimwear、see-through fabric、kissing、touching her own body suggestively,再加上多手指、手变形、画面文字、水印这类防崩坏条目。
还有一个我们看过成片后改掉的地方:格子百褶短裙配白袜,画出来像校服。只要是带暧昧氛围的场景,这类搭配一律不用,任何会让成年人物看起来更小的元素也一样。
每一组是同一个人物:左边是 Muse Image 设定图,右边是 10 秒、720×1280 的 Muse Video 成片截图。每组下面是原样发出去的视频提示词。完整视频可以在 Muse Video 模型页的案例里看。
从设定图到成片,脸、米白针织上衣和金色圈形耳环都没变。
设定图里是棕色长卷发、米白罗纹方领上衣、浅色牛仔裤和金色圈形耳环。截图里她隔着放着两杯冰拿铁的桌子正在说话,上衣和耳环与设定图一致,背后的顾客是虚化的。
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. Coffee date. Scene: a sunny corner café, window seat, a small wooden table with two iced oat lattes, soft morning light through the window, the street blurred outside, a few customers far in the background. Camera: the viewer's point of view, sitting across the table from her, eye level, one continuous take, no cuts. 0.0–1.5 s: she rests her chin on one hand and stirs her latte with the straw, looking down with a small smile. 1.5–3.0 s: she looks up into the lens, raises one eyebrow and her smile widens. 3.0–5.0 s: she says, warm and teasing: "Took you long enough. I already ordered yours." and slides the second latte toward the camera with two fingers. 5.0–7.0 s: she tucks a strand of hair behind her ear and leans forward a little on her elbows, holding eye contact, with a soft laugh. 7.0–8.5 s: she taps the table twice and tilts her head toward the empty chair, inviting the viewer to sit. 8.5–10.0 s: she sips her latte and keeps looking into the lens over the straw, eyes smiling, until the end. Mood: warm, playful, confident, friendly; natural eye contact, nothing exaggerated. Lighting: soft warm daylight, gentle highlights in her hair, realistic skin texture. Audio: soft acoustic café music and light café 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, natural colors, crisp focus on her face, gentle handheld motion. Avoid: changing her face or outfit, revealing or low-cut clothing, see-through fabric, extra fingers, warped hands, strangers staring at the camera, on-screen text, subtitles, watermark.
白色亚麻衬衫裙和棕色腰带都保留了,按提示词光着脚。
设定图是金色长卷发、系棕色腰带的白色亚麻衬衫裙、卷起的袖子和棕色凉鞋。截图里她站在海边浪花处,同样的裙子和腰带,迎着低低的夕阳回头看镜头。
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. Golden hour beach. Scene: a wide sandy beach at sunset, gentle waves, the sun low over the ocean, footprints in wet sand, a light sea breeze. Camera: the viewer walking a few steps behind her, one continuous take, smooth natural movement. 0.0–2.0 s: she walks barefoot along the waterline away from the camera, sandals hanging from one hand, the breeze moving her hair and the hem of her shirt dress. 2.0–3.5 s: she slows down and looks back over her shoulder at the lens with a bright smile. 3.5–5.5 s: she turns around, walks backwards for a few steps and reaches one hand toward the camera, palm up, saying: "Come on, the sun's going down!" 5.5–7.5 s: the camera moves closer; she laughs and pushes her windblown hair off her face, eyes on the lens. 7.5–9.0 s: she takes a little splash step in the shallow water and glances back with a playful grin. 9.0–10.0 s: she stops and faces the camera with the sunset behind her, tilts her head and smiles softly, holding eye contact. Mood: carefree, warm, inviting, romantic but natural. Lighting: golden backlight, soft lens flare, warm skin tones, rim light on her hair. Audio: dreamy indie pop music with soft waves and wind; her line is clear, natural American English; no other voices, no laugh track. Style: realistic Instagram Reel shot on an iPhone, vertical 9:16, natural colors, crisp focus on her face, gentle handheld motion. Avoid: changing her face or outfit, revealing or low-cut clothing, see-through fabric, extra fingers, warped hands, strangers staring at the camera, on-screen text, subtitles, watermark.
连大头照里的雀斑都出现在了成片里。
设定图是黑棕色长卷发、雀斑、白色一字肩罗纹针织衫、牛仔短裙和白色运动鞋。截图里她在条纹遮阳棚下端着粉色杯子喝咖啡,穿着同一件针织衫和短裙,雀斑清晰可见。
Reference images: image 1 is her headshot (face, features, hair, makeup); image 2 is a front / side / back three-view of the same woman in a light summer outfit (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. Outdoor café date. Scene: a sunny café terrace on a quiet European-style street, a small round marble table with two cappuccinos and a croissant, a striped awning, potted flowers, soft morning sun. Camera: the viewer's point of view sitting across the small table, very close to her, eye level. 0.0–1.5 s: she rests her chin on her interlaced fingers, watching the lens with a slow half-smile. 1.5–3.0 s: she reaches across, takes the viewer's cappuccino instead of her own and sips it, eyes on the lens over the cup. 3.0–4.5 s: she wipes a little milk foam from her lip with her thumb and laughs. 4.5–6.0 s: she says, teasing: "Mine's better." and slides her own cup toward the camera. 6.0–8.0 s: she leans in close to the lens on her elbows, her bare shoulders catching the sun, lightly bites her lower lip and holds eye contact. 8.0–10.0 s: she leans back, tucks her hair behind her ear and gives one playful wink. Lighting: soft warm morning sun, gentle highlights on her hair and shoulders. 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. She is clearly enjoying the viewer's company. Audio: light French café jazz and soft street 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.
在暖色台灯下,红棕色刘海短发和锈橙色针织连衣裙都保持住了。
设定图是带空气刘海的红棕色波浪短发、锈橙色罗纹短袖针织连衣裙和棕色麂皮短靴。截图里她坐在花纹扶手椅上、台灯旁边看书,裙子和发型与设定图一致。
Reference images: image 1 is her headshot (face, features, hair, makeup); image 2 is a front / side / back three-view of the same woman in a light summer outfit (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. Bookstore reading nook. Scene: a cozy window seat in an independent bookstore, cushions, stacks of books, warm lamp light mixed with late-afternoon sun. Camera: the viewer sitting down next to her on the window seat, close. 0.0–1.5 s: she sits curled up on the window seat reading an open book, a strand of hair falling across her face. 1.5–3.0 s: she glances up over the top of the book at the lens, then back down, hiding a smile. 3.0–5.0 s: she lowers the book and says softly: "This part reminds me of you." 5.0–7.0 s: she shifts closer and holds the open book toward the camera, her face close to the lens. 7.0–8.5 s: she watches the viewer's reaction, lightly bites her lower lip and laughs quietly. 8.5–10.0 s: she closes the book against her chest, tilts her head and holds eye contact with a soft smile. Book pages and covers stay plain, with no readable text. Lighting: warm amber lamps, soft window light on her face. 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. She is clearly enjoying the viewer's company. Audio: soft piano and acoustic guitar music with a quiet bookstore 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.
Muse Image 每张 $0.02,带不带参考图都一样。Muse Video 按请求的秒数计费,每秒 $0.037。一个人物的设定图只付一次 $0.02,之后每条视频只付视频的钱。失败的请求不扣费。价格为 apimodels.app 2026-11-01 的标价。
| 项目 | 价格 | 说明 |
|---|---|---|
| 人物设定图(Muse Image) | $0.02 | 每次 1 张,约 250 万像素 |
| 5 秒视频 | $0.185 | 720p,横屏或竖屏 |
| 10 秒视频 | $0.37 | 通常一个镜头,提示词写 one continuous take |
| 15 秒视频 | $0.555 | 大约第 10 秒换镜头 |
| 30 秒视频 | $1.11 | 大约第 10、20 秒换镜头 |
| 失败的请求 | $0 | 不扣费 |
Muse Image: 约 250 万像素(1:1 是 1600×1600,16:9 是 2048×1152),没有 4K,不支持透明背景、反向提示词和 seed,每次只出 1 张。
Muse Video: 只有 720p,只有 16:9(1280×720)和 9:16(720×1280),4 到 30 秒的整数秒,要么 1 张首帧、要么最多 4 张参考图(二选一)。超过 10 秒会在大约第 10、20 秒自己换镜头。10 秒以内一般 1 到 2 分钟出片,15 到 30 秒一般 3 到 7 分钟。
不保证每次都成功。 失败不扣费,但要自己做重试。另外,提示词里不要写一个和时长参数矛盾的总时长:参数是 8 秒、提示词写「about 7.5 seconds」,出来的片会更短。
这些情况别用: 需要 4K 静图、需要超过 10 秒的一镜到底、或者每次都必须出片的业务。另外,绝不要拿真实人物的照片做人物:AI 网红应该是虚构的,而不是照着某个没同意过的人去复制。
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"))不要只靠提示词:Muse 没有 seed,同一段话每次画出来的人都不一样。先用 Muse Image 出一张设定图,裁成大头照和三视图两张,作为参考图传给 Muse Video,并在提示词里说明每张图管什么。之后每个新场景都复用这两张图。
在 apimodels.app 上,一条 10 秒的 Muse Video 视频是 $0.37(按请求秒数每秒 $0.037)。人物设定图 $0.02,一个人物只付一次,所以新人物的第一条视频是 $0.39,之后每条 $0.37。失败的请求不扣费。
把暧昧感放在动作上,不放在衣服上:看镜头、慢慢的半笑、轻咬下唇、凑近镜头、最多眨一次眼,并注明「natural and playful, never explicit」。衣服可以露肩、手臂和腿,但要写「modest neckline, no cleavage」,提示词最后用 Avoid 行排除乳沟、内衣、泳装、透视和亲吻。
「18 岁」「学生」「新生」「清纯少女」这类词会把 Muse 往更小的年纪拉,我们自己测试时就遇到过。在设定图和视频提示词里都写具体的成年年龄(「a 25-year-old woman」),并避开像校服的搭配,比如格子百褶短裙配白袜。
Muse Video 支持 4 到 30 秒的整数秒,720p,16:9 或 9:16。超过 10 秒的会在大约第 10、20 秒换镜头,所以 30 秒是三个镜头;更短的片子偶尔也会自己切一下。要一镜到底,就控制在 10 秒以内,并在提示词里写「one continuous take」。
只能用你自己、或者明确同意过的人的照片。明星、朋友、网上找的图都不应该被做成 AI 网红,更不能把真实的人放进对方没同意过的暧昧内容里。人物应该用设定图从零虚构。
