跳到主要内容
Kyeo AI
AI 视频模型
Google
Veo

Veo3.1 Fast

用文字、首尾帧或参考图生成视频，选择需要的画幅、时长和分辨率。直接生成预计预扣 30～90 积分；参考图模式须选择 8 秒。

使用这个模型查看积分价格返回模型广场
输入方式
文字、首尾帧、参考图
预计预扣
720p 30 · 1080p 38 · 4K 90 积分
提示词上限
5,000 字符
上传限制
JPEG / PNG，每张最多 10 MB
快速了解
  • 可用文字、首尾帧或 1～3 张参考图生成视频。
  • 直接生成可选 720p、1080p 和 4K，各档预计积分不同。
  • 参考图模式仅支持 16:9 或 9:16，时长须选 8 秒。
  • 成功的基础任务可以延长；符合条件的结果可另行获取 1080p 或 4K 版本。

相关查询: Veo3.1 Fast 怎么用 · Veo3.1 Fast 参考图怎么用 · Veo3.1 Fast 价格

示例

Cinematic scene

Create a professional cinematic jewelry advertisement storyboard board. Aspect ratio: 16:9 horizontal layout. Theme: Pearl and crystal jewelry elegance. Duration: 15 seconds. Style: High-end fashion editorial presentation, cinematic jewelry film, soft feminine atmosphere, minimal modern studio aesthetic, refined craftsmanship, elegant beauty photography. Color palette: Pearl white, soft champagne gold, warm ivory, black velvet, soft blush pink, subtle silver highlights. Visual direction: Delicate pearl textures, sparkling gemstone reflections, silky fabric movement, soft candle-like highlights, clean elegant compositions, beautiful macro details. No brand. No logo. No text. No watermark. No readable symbols. --- MAIN SUBJECT: A young adult Asian woman with an elegant and natural appearance. Appearance: Soft refined facial features. Long dark hair with gentle waves. Natural glowing skin. Calm confident expression. Graceful posture. Minimal elegant makeup. Wardrobe: Flowing ivory silk dress. Soft fabric texture. Elegant modern fashion silhouette. No visible patterns or logos. --- JEWELRY DESIGN: A delicate pearl and gemstone jewelry collection. Includes: Pearl necklace. Pearl earrings. Elegant gemstone bracelet. Fine metallic details. Design: Smooth natural pearl surfaces. Clear crystal reflections. Fine metal craftsmanship. Minimal timeless shapes. No recognizable brand designs. --- STORYBOARD STRUCTURE: 8 SHOTS · 15 SECONDS · CINEMATIC JEWELRY FILM --- SHOT 1 — THE INTRODUCTION Duration: 0:00–0:02 Wide cinematic shot. The woman stands beside a large window in a softly illuminated room. Morning light enters through sheer curtains. A jewelry display rests nearby on a dark velvet surface. Camera: Slow elegant push-in. Mood: Quiet elegance. --- SHOT 2 — THE PEARL DETAIL Duration: 0:02–0:04 Extreme macro shot. A single pearl necklace rests on soft fabric. Light moves slowly across the pearl surface. Show: smooth texture, soft reflections, delicate craftsmanship. Camera: Macro beauty photography. --- SHOT 3 — THE HANDCRAFT MOMENT Duration: 0:04–0:06 Close-up. The woman's hands gently pick up pearl earrings. Her fingers move carefully. The gemstones reflect soft light. Camera: Slow focus pull. Lighting: Warm highlights. --- SHOT 4 — THE PREPARATION Duration: 0:06–0:08 Medium beauty shot. The woman puts on the pearl earrings. Her hair moves naturally. The jewelry catches the light. Camera: Elegant side profile. Atmosphere: Soft and graceful. --- SHOT 5 — THE REFLECTION Duration: 0:08–0:10 Close-up portrait. The woman looks into a mirror. Pearls and gemstones create subtle reflections. She smiles gently. Camera: Slow cinematic orbit. --- SHOT 6 — THE JEWELRY MOVEMENT Duration: 0:10–0:12 Macro cinematic shot. The necklace moves slightly as she walks. Pearls catch the surrounding light. Fabric flows naturally. Camera: Slow motion fashion movement. --- SHOT 7 — THE COMPLETE LOOK Duration: 0:12–0:14 Full-body fashion composition. The woman walks through an elegant bright interior space. Soft curtains move behind her. Jewelry remains the visual focus. Camera: Smooth tracking shot. --- SHOT 8 — FINAL HERO FRAME Duration: 0:14–0:15 Final product beauty shot. Pearl necklace and earrings displayed on velvet surface. The woman softly appears in the background. Warm light creates a timeless atmosphere. Camera: Slow push-in. --- LIGHTING: Soft diffused lighting. Pearl-like highlights. Warm champagne reflections. Gentle shadows. Cinematic depth. Elegant glow. --- CAMERA STYLE: Fashion editorial camera. Macro jewelry photography. Slow dolly movement. Smooth tracking. Shallow depth of field. Professional commercial composition. --- NEGATIVE: brand name, logo, watermark, text, letters, celebrity, famous person, recognizable jewelry design, copyrighted design, exaggerated luxury symbols, money, wealth symbols, unrealistic gemstones, plastic skin, distorted hands, bad anatomy, low quality, blurry.

Cinematic scene

Create a 30-second, 1080p ultra-realistic home video of the same young adult woman spending an unplanned afternoon in a quiet coastal neighborhood. Character: Natural expressive face, warm brown eyes, realistic skin, long dark-brown messy ponytail. Ivory oversized linen shirt, muted-blue camisole, sand-colored trousers, white sneakers, brown crossbody bag, silver hoops and watch. Maintain exact identity, outfit, hairstyle, proportions, and accessories throughout. Setting: Authentic seaside residential streets with weathered homes, narrow lanes, plants, bicycles, laundry, ocean glimpses, and a waterfront path. No brands, landmarks, advertisements, or staged crowds. Camera: Older handheld consumer camera operated by a friend. Imperfect framing, natural shake, autofocus hunting, exposure shifts, motion blur, digital noise, and compression. No gimbal, drone, slow motion, or polished commercial look. Sequence: 0–5s: She exits carrying a paper bag, checks her phone, and laughs when wind catches her shirt. 5–10s: She notices colorful kites, stops to watch, and the camera briefly loses focus. 10–15s: A child's kite catches on a fence; she gently frees it and returns it, creating a natural spontaneous moment. 15–20s: She walks toward the sea and quietly watches the water as wind moves her hair and clothing. 20–25s: Ocean spray surprises her; she laughs, looks toward the camera, and wipes water from her face. 25–30s: Warm sunlight breaks through clouds. She smiles subtly at the camera, then walks away beside the ocean. Hard cut to black at 29.5s. Realism: Accurate physics, natural walking, hair, fabric, paper, kite strings, seawater, lighting, shadows, hands, and facial expressions. No distortions, duplicated objects, disappearing props, wardrobe changes, or anatomy errors. Audio: Natural wind, ocean, birds, footsteps, bicycles, neighborhood ambience, paper rustling, and genuine laughter. No music, narration, subtitles, captions, logos, or watermarks. Final feel: A beautiful but ordinary moment accidentally captured by a friend—intimate, imperfect, spontaneous, and genuinely real.

Cinematic scene

SEEDANCE 2.5 | 30s | 16:9 | ULTRA-PHOTOREALISTIC SMARTPHONE VLOG A genuine personal smartphone travel vlog of a Korean woman in her early 20s experiencing Istanbul for the first time. Spontaneous, natural and slightly imperfect — never a tourism commercial. CHARACTER: Same Korean woman throughout. Petite oval face, expressive brown eyes, long black hair with loose strands, realistic fair skin and natural imperfections. Cream ribbed top, dark-brown wide-leg trousers, open beige trench coat, brown crossbody bag, white sneakers, delicate gold jewelry. No identity or wardrobe changes. She speaks only Turkish with a natural Korean accent, slightly imperfect and conversational. No subtitles, captions or translations. CAMERA: Handheld smartphone, 16:9 landscape. Natural arm movement, walking jolts, imperfect framing, autofocus delays, exposure shifts, realistic motion blur and phone-camera texture. No gimbal, drone, cinematic lens effects or commercial grading. STORY 0–4s — HAGIA SOPHIA: Selfie walk through Sultanahmet with Hagia Sophia behind her. She turns the camera toward it, then back to herself and says: “Vay… Ayasofya gerçekten çok güzel.” 4–7s — BLUE MOSQUE: Show the Blue Mosque, square, pigeons and pedestrians. She walks through frame, looking around with quiet curiosity. 7–11s — TOPKAPI: She explores Topkapı Palace courtyards and architecture, briefly showing the Bosphorus. She says: “Burası çok eski… çok güzel.” 11–14s — BREAKFAST: Local café table with simit, cheese, olives, eggs and Turkish tea. She takes a bite of simit and says: “Bu kahvaltı çok güzel!” 14–17s — COFFEE: Close handheld shot of Turkish coffee being prepared and poured. She sips, reacts naturally and says: “Kahve çok güçlü!” She laughs. 17–20s — GRAND BAZAAR: Busy authentic bazaar with lamps, ceramics, textiles and pedestrians. She films while walking and casually moves aside as someone passes. 20–23s — GALATA / İSTİKLAL: Galata Tower, historic streets and red tram. She looks up, turns to camera and says: “İstanbul çok güzel bir şehir.” 23–27s — BOSPHORUS: Golden-hour ferry selfie. Wind moves her hair and trench coat. She turns toward the Bosphorus, ferries, seagulls and bridges, then softly says: “Burası inanılmaz…” 27–30s — NIGHT: Warm Istanbul street lights, taxis, pedestrians and trams behind her. She smiles at the camera and says: “İstanbul, seni çok sevdim. Tekrar geleceğim!” She raises her hand and naturally covers the lens. AUDIO: Authentic Istanbul ambience — traffic, trams, ferries, seagulls, footsteps, vendors, cafés, wind and pedestrians — mixed with a subtle upbeat travel soundtrack. Natural Korean-accented Turkish dialogue. REALISM LOCK: Authentic Istanbul locations, realistic crowds, food, coffee, ferry movement, wind, shadows, reflections, skin, hair and fabric physics. Natural expressions and imperfect camera behavior. NEGATIVE: No face drift, duplicate people, distorted hands, floating objects, fake crowds, plastic skin, beauty filter, exaggerated reactions, impossible architecture, teleporting, subtitles, captions, text, logos, watermark, CGI or tourism-commercial aesthetic.

Cinematic scene

6 shots, total 30s 0.0-5.0s, 5.0-10.0s, 10.0-15.0s, 15.0-20.0s, 20.0-25.0s, 25.0-30.0s. Hard cuts, no dissolves. Normal speed throughout, no slow motion, no ramping. CAPTURE CADENCE CRITICAL: native 24fps, true 180-degree shutter, real 1/48s exposure every frame. Fluid, continuous motion blur. Never choppy, never juddering. No interpolation, no ghosting, no video look. NO ON-SCREEN TEXT CRITICAL: no text of any kind anywhere in frame. No captions, subtitles, titles, credits, watermarks, logos, timecode, UI overlays. NOBODY ELSE IN FRAME CRITICAL: no monks, villagers, or extras. Only the swordsman, the oni, and one crow are ever visible. THE FIRE CRITICAL: burning temple embers drift and flare through every frame, occasionally flaring bright enough to strobe-light a beat. The stepped quality of any lit moment comes entirely from ember-flare, never from broken footage camera motion stays smooth throughout. Falling ash rakes diagonally, screen-left to right. Subject Lock the swordsman: lean weathered build, closecropped greystreaked hair, hard jaw, sootstreaked skin, clean face, no tattoos. Charcoal hakama and a scorched indigo haori, one steel pauldron, straw sandals. Grips a curved katana two-handed. Advances through the burning temple courtyard toward the oni, stance low and controlled through every strike. Subject Lock the oni: towering horned demon, no visible pores cracked obsidian-red skin glowing along fault lines with molten orange light, tusked jaw, matted black mane. Carries a massive iron kanabo studded with spikes. Advances with heavy ground-shaking steps, never runs. World Plate: a burning temple courtyard at night a shattered stone torii gate, a collapsing pagoda roof shedding tile, a wide gravel yard scattered with broken lanterns, distant burning rooftops beyond the temple wall. No other structures stand whole. THE ATMOSPHERE CRITICAL, depth only: heavy smoke haze at high density swordsman sharp near, oni softened at mid-distance, burning rooftops near-erased far. Thickened smoke-air only, never a fog-machine look. SHOT 1 0.0-5.0s. THE ADVANCE. Low camera at gravel level, cant 15°, tracking the swordsman forward. Swordsman strides through drifting embers, katana raised, oni looming ahead. Swordsman screenleft advancing, oni screen-right filling the yard. Diegetic sound. SHOT 2 5.0-10.0s. THE CLASH. Camera orbits tight at chest height, cant swinging 15-35°, never square. Katana rings off the kanabo in a shower of sparks, swordsman thrown back a step. Both centered, gravel kicking up. Diegetic sound. SHOT 3 10.0-15.0s. THE OMEN. Cut to a crow bursting off the collapsing pagoda roof as tile showers down. It wheels hard away from the falling debris. Crow centered against the burning roofline. Diegetic sound. SHOT 4 15.0-20.0s. THE COLLAPSE. Low static camera in the courtyard, whip-panning up as the pagoda roof gives way. The roof section tears free and crashes into the yard; the swordsman rolls clear through gravel and ash. Roof beam diagonal across frame, swordsman emerging low center. Diegetic sound. SHOT 5 20.0-25.0s. THE SURGE. Camera drops to ground height, rockets forward through a corridor of drifting embers lit by a flare of firelight. Swordsman sprints low, katana trailing sparks, closing on the oni's flank. Swordsman screen-left driving right. Diegetic sound. SHOT 6 25.0-30.0s. THE AFTERMATH. Camera pulls back to a wide static courtyard frame, embers settling, wind dying. The swordsman stands alone, katana lowered, chest heaving, as the oni's glowing fault-lines dim to black and it topples out of frame. Swordsman small and centered, burning pagoda dark behind. Diegetic sound. Cross-Frame Rules: swordsman's haori, pauldron, and sandals never change. Oni's fault-line glow never fully fades until Shot 6. Only swordsman, oni, and crow ever visible. Ash direction stays constant. Pagoda keeps the same silhouette wherever it appears. Ember-flare applies only inside Shots 1, 2, and 5. No score enters at any point. Last Frame: the swordsman stands alone in the courtyard, katana lowered, embers drifting down around him, the oni's dark fallen shape at the frame's edge, the pagoda's broken silhouette burning low behind. No on-screen text, no logo, no watermark. Sound Bed: diegetic only — crackling fire, falling tile, katana ringing off iron, the oni's low guttural roar, gravel crunching underfoot, a crow's sharp cry. No score, no subtitles. Camera & Capture Realism: ~32mm/68° FOV, vintage 2x anamorphic with oval bokeh and streak flares off the firelight, shallow depth of field, color-negative rendition, fine grain. Violent handheld cant swinging 15-45°, punching in and ripping back, every frame mid-move but smooth in its own travel, never locked, never gimbalglide. No CGI look, no AI smoothness, no videogame HUD, no motion smoothing.

Cinematic scene

用 iPhone 拍摄的真实感短视频，9:16，15秒。不要电影感，不要炫光， 不要体积光。自然平光，略微过曝，画面偏灰发白，像手机随手拍。 真实纪录片质感，轻微手持抖动，偶尔失焦，运动模糊。 【0-4秒｜拆弹】普通水泥地下室，顶部一盏廉价日光灯管，平淡冷白光， 没有戏剧光影。一名穿旧防爆服的人俯身在一个锈金属箱上， 箱上红色数字 00:06 跳动，红蓝线缠绕。手机怼脸拍，画质普通， 背景虚化很浅，有噪点。剪线钳夹住红线。表情紧张但不夸张。 【4-7秒｜反转】咔嚓——不是爆炸，一股白蒸汽"嘶"喷出。 箱子弹开露出一台普通家用意式咖啡机。他愣住。手机慌乱晃动， 自动对焦来回拉风箱。平光，无滤镜。 【7-11秒｜咖啡】手机微距怼近白瓷杯，浓咖啡注入，crema油泡， 热气。光线普通室内光，不是影棚。略微手抖，不完美对焦。真实。 【11-13.5秒｜落点】他摘头盔，一脸疲惫平静地喝了一口， 背后墙壁普通脏旧，没有god ray光束。日常平光。deadpan。 【13.5-15秒｜品牌】切纯白背景，居中标志："PILA"红色粗体， 下方 "SERIOUSLY GOOD COFFEE"，金色咖啡豆图形。 关键：全片模仿手机随手拍，不要专业布光，不要高对比， 不要湿润高光和CGI光泽。要平、要糙、要真实的皮肤毛孔和哑光布料。 每个镜头只用一个运镜。

Cinematic scene

Cinematic fashion film of a young woman with long dark wavy hair walking through New York City. She wears oversized brown tortoiseshell sunglasses, gold hoop earrings, a cream sherpa fleece jacket with black leather trim and toggle buttons, a black mini skirt, black tights, and chunky black loafers, carrying a small black shoulder bag. Sequence: she exits a glass-door building, crosses a busy intersection with yellow taxis, glances into a café window, walks the sidewalk, buys a cold water bottle from a street cart, drinks it, sits on a green park bench, then walks away. Natural daylight, golden-hour highlights, smooth handheld and tracking shots, close-ups of her face, hair, and outfit details. Aesthetic street-style, 4K, filmic color grade, shallow depth of field.

一句话了解

这个模型怎么样？

先选文字生成或图生视频。图生视频可以用首帧、首尾帧，或 1～3 张参考图；参考图模式仅支持横向 16:9、竖向 9:16 和 8 秒时长。提交后等待结果，先检查主体、动作和声音，再决定是否延长视频或获取更高分辨率的版本。

模型定位
Veo3.1 Fast 是 Kyeo AI 提供的视频生成模型之一，可从文字、首尾帧或参考图开始制作。
适合谁用
可用于尝试产品动态镜头、人物短镜头或带参考图的场景。先做一个主要动作，检查结果是否符合要求，再安排后续制作。
本站使用说明
在工作台选择输入模式和规格，查看积分提示并提交。生成结果和符合条件的后续操作可以在同一个账号内查看。

关键参数一览

根据这些信息，判断模型是否适合你的任务。

模型类别
AI 视频模型
厂商
Google
模型家族
Veo
可用位置
Kyeo AI 工作台
运行方式
提交后等待结果
提示词上限
5,000 字符
上传限制
首尾帧最多 2 张，参考图最多 3 张；每张最多 10 MB

它还叫什么

同一个模型在公开资料中可能有不同名称，这里整理相关称呼，方便查找和比较。

Veo3.1 Fast
Google Veo
Veo Video

用户常见问题

从任务、输入条件和结果要求出发，整理选择模型时需要确认的问题。

Veo3.1 Fast 怎么用
Veo3.1 Fast 参考图怎么用
Veo3.1 Fast 价格
Veo3.1 Fast 和 Quality 区别
Veo3.1 Fast 和 Lite 区别
Veo3.1 Fast 支持几张参考图
Veo3.1 Fast 怎么延长视频
Veo3.1 Fast 获取 1080p 视频
Veo3.1 Fast 生成 4K 视频
Veo3.1 Fast 时长和图片要求

选型指南

根据输入素材、任务要求和积分成本，逐项确认模型是否适合。

1
已有素材时怎么开始

只有一张起始图片，可先试首帧生成；需要指定起点和终点，可用首尾帧。想同时参考多张图时，选择参考图模式，并确认横向或竖向画幅和 8 秒时长符合任务要求。

2
先比较版本和积分

Lite、Fast 和 Quality 的输入模式及预计积分可能不同。用相近的素材和共同支持的规格比较，记下实际积分和结果；版本名称本身不能保证某次结果更符合要求。

3
提交前列出检查项

写下主体、动作、镜头和必须保留的细节，核对输入要求与积分提示。生成后按这些要求查看视频和声音，再保存需要的结果；需要帮助时可通过联系页面咨询。

模型对比

把常见候选放在同一任务下比较，帮助你确认输入方式、控制项和成本差异。

使用多张参考图时，怎样核对 Fast 与 Lite 的画幅和时长限制？
按同一分辨率制作视频时，Fast 与 Lite 的预扣预算和确认消耗应怎样比较？
已有多张人物或物品素材时，怎样核对 Fast 与 Quality 的参考图输入方式？
用相同首尾帧试做镜头时，怎样比较 Fast 与 Quality 的动作衔接和声音结果？
延长成功视频时，怎样核对 Fast 的来源条件，并查看 Sora 2 Pro 是否提供相应操作？
从文字起稿时，怎样查看 Fast 与 Sora 2 Pro 各自的时长和画幅选项？

模型横向对比表

按同一组维度比较当前模型和候选模型的输入、设置与使用边界。

版本
Veo3.1 Fast
Fast
Veo3.1 Lite
Lite
Veo3.1 Quality
Quality
生成模式
Veo3.1 Fast
文字、首尾帧、参考图
Veo3.1 Lite
文字、首尾帧、参考图
Veo3.1 Quality
文字、首尾帧；没有参考图模式
结果操作
Veo3.1 Fast
成功的基础任务可延长；符合条件的基础或延长结果可获取 1080p、4K 版本
Veo3.1 Lite
可延长基础任务；符合条件的结果可获取 1080p、4K 版本
Veo3.1 Quality
可延长基础任务；符合条件的结果可获取 1080p、4K 版本
直接生成的预计预扣
Veo3.1 Fast
720p 30 · 1080p 38 · 4K 90 积分
Veo3.1 Lite
720p 15 · 1080p 23 · 4K 75 积分
Veo3.1 Quality
720p 225 · 1080p 233 · 4K 285 积分
选择前检查
Veo3.1 Fast
确认需要的输入模式、输出规格和预计积分
Veo3.1 Lite
按相同规格比较预计积分和实际结果
Veo3.1 Quality
先核对预算，再按相同规格比较实际结果

适用情况

依据公开资料与当前站内设置，说明模型适用的任务及需要注意的限制。

按当前设置选择

同一系列的版本可能提供不同输入和规格。选择前查看对应模型详情页，再到工作台确认本次任务可用的模式和参数。

把后续制作计入预算

延长视频和获取 1080p、4K 版本都是另外提交的任务，会另行预扣积分。先检查基础结果，再按需要选择后续操作，并在积分明细中核对结算。

能力详解

从文字或图片开始

文字模式不用上传图片。首尾帧模式接受 1～2 张图片；参考图模式接受 1～3 张图片。每张须为 JPEG 或 PNG，且不超过 10 MB。

用多张图片作参考

参考图模式可配合文字说明主体、造型或场景。须选择 16:9 或 9:16 和 8 秒时长；提交后仍需检查关键细节，图片中的内容不保证完整保留。

在成功结果上继续制作

只有本人成功的基础任务可以延长。本人成功的 720p 基础任务或延长结果可获取 1080p、4K 版本；直接生成的 1080p、4K 结果不能再次执行获取更高分辨率的操作。

适合做什么

产品动态镜头

用产品图片作首帧，描述一个主体动作或镜头运动。生成后检查轮廓、标志和文字，再决定是否用于后续剪辑。

带参考图的场景

准备能说明主体、造型或环境的图片，在文字中写清每张图要提供什么参考。按支持的画幅和时长生成后，检查主体和场景是否符合要求。

继续制作已有镜头

基础视频符合要求后，可在成功结果中选择延长。需要更高分辨率时，先检查结果是否满足操作条件，再单独提交。

提示词技巧

先选择输入模式

根据手头素材选择文字、首尾帧或参考图，再写清主体、动作、环境和镜头。参考图模式有固定的画幅和时长要求，先确认这些条件。

说明每张参考图的用途

使用多张参考图时，在文字中说明每张图提供的主体、造型或环境，以及哪些细节需要保留。生成后按这些要求逐项查看。

先检查基础结果

主体、动作或声音不合适时，先调整基础任务。延长和获取更高分辨率的版本都会另行预扣积分，也不能保证修正原视频中的问题。

为什么选它

输入模式包括文字、首尾帧和多张参考图，可按现有素材选择。
可直接选择 720p、1080p 或 4K，并在提交前查看预计积分。
时长可选 4、6 或 8 秒；参考图模式固定为 8 秒。
符合条件的成功结果可以继续延长，或另行获取 1080p、4K 版本。

使用前要知道

参考图模式不接受自动画幅，须选 16:9 或 9:16，时长须为 8 秒。
获取 1080p、4K 版本仅适用于本人成功的 720p 基础任务或延长结果。已经获取的版本不能重复作为这类操作的来源。
不能保证每次都生成符合要求的声音。用于发布或剪辑前，检查画面、动作、声音和关键细节。
图片须为 JPEG 或 PNG，每张不超过 10 MB。首尾帧最多 2 张，参考图最多 3 张；重要文字、形状和角色细节仍需检查。

可调参数

根据这些信息，判断模型是否适合你的任务。

生成模式
可选
参数类型: 选项
文字模式无需图片；图生视频可选择首尾帧或参考图模式
文字生成视频
首尾帧模式
参考图模式
宽高比
可选
参数类型: 选项
16:9
横向（16:9）
竖向（9:16）
自动（参考图模式不可用）
分辨率
可选
参数类型: 选项
720p
720p：预计 30 积分
1080p：预计 38 积分
4K：预计 90 积分
时长
可选
参数类型: 选项
8 秒
4 秒
6 秒
8 秒（参考图模式仅此选项）
水印文本
可选
参数类型: 文字
提示词翻译
可选
参数类型: 选项
自动翻译为英文
自动翻译为英文
保留原文

积分消耗

预计 30～90 积分

直接生成时，720p 预计预扣 30 积分，1080p 预计预扣 38 积分，4K 预计预扣 90 积分。延长视频另行提交，预计预扣 30 积分；符合条件的结果获取 1080p 或 4K 版本，分别预计预扣 8 或 60 积分。任务结束后按确认的实际消耗结算，可在积分明细中核对扣点和退还。

使用建议

准备多次生成时，建议先用少量素材测试，核对输入设置和结果是否适合任务，再决定是否继续。每次生成均按工作台显示的计费规则扣点。

常见问题

相关模型

按你的任务比较这些模型的输入要求、功能和当前状态，再查看对应详情。

Veo3.1 Lite

从文字、首尾帧或参考图开始制作视频，直接生成的预计预扣为 15～75 积分。分辨率可选 720p、1080p 和 4K；参考图模式须选 8 秒。

AI 视频模型
预计 15～75 积分
查看详情立即使用

Veo3.1 Quality

用文字描述想要的视频，或上传单张首帧、两张首尾帧。Veo3.1 Quality 可选择视频时长与 720p、1080p、4K 分辨率，预扣积分随分辨率变化。生成后可对符合条件的结果发起延长或升分辨率；每项操作都另预扣积分。

AI 视频模型
720p／1080p／4K 分别预扣 225／233／285 积分
查看详情立即使用

Seedance 2.5

用 Seedance 2.5 规划较长镜头，先选择文字、首帧与首尾帧或多模态参考场景。请求时长可设为最长 30 秒；默认 5 秒，选择自动时长则按 30 秒预留预计积分。准备素材时，数量、单段时长与累计时长需分别核对。

AI 视频模型
预计预扣 102–5,700 积分
查看详情立即使用

信息来源

页面内容依据公开模型资料与 Kyeo AI 的模型信息整理。能否在线使用，请以当前模型状态为准。

来源说明

本页参考下方 Google Cloud 的 Veo 型号资料、接口参考与更新记录，官方资料用于了解版本和服务背景。Fast 在 Kyeo AI 的模式、输入条件、直接生成规格以及结果操作按本站当前设置说明；这些选项与预计预扣需在工作台核对，官方资料不代表本站开放相同功能或保证输出效果。

内容复核日期: 2026-08-28
Google Cloud：Veo 3.1 模型规格
官方
查看原始来源
Google Cloud：在线预测 API 参考
官方
查看原始来源
Google Cloud：模型更新记录
官方

Google 的模型更新记录。本站当前可用设置请查看模型详情和工作台。

查看原始来源