跳到主要内容
Kyeo AI
AI 视频模型
Google
Veo

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。

使用这个模型查看积分价格返回模型广场
生成方式
文字或首尾帧
直接生成预扣积分
720p 225 · 1080p 233 · 4K 285
提示词上限
5,000 字符
图片要求
JPEG／PNG · 最多 2 张 · 每张 10 MB 以内
快速了解
  • 直接生成可选 720p、1080p、4K，预扣积分随分辨率变化
  • 不上传图片时使用文字生成；单张图片作为首帧，两张作为首尾帧
  • 可选 4、6 或 8 秒，默认 8 秒
  • 图片须为 JPEG 或 PNG，最多 2 张，每张不超过 10 MB；不支持参考图模式

相关查询: Veo3.1 Quality 怎么用 · Veo3.1 Quality 积分 · Veo3.1 Quality 和 Fast 区别

示例

Cinematic scene

Generate a video with the following specifications: Duration: 15 seconds Aspect Ratio: 16:9 Frame Rate: 24 fps 85mm prime lens with extremely subtle handheld breathing motion. Japanese airy film aesthetic blended with authentic Indonesian university life. Kodak Portra 400 cinematic color science, fine film grain, soft bloom, gentle gray haze, documentary-style realism. Primary color palette: Warm cream campus buildings, soft green trees, TransJakarta blue, MRT white and blue, cozy coffee shop browns, rainy gray skies, orange sunset, natural skin tones. Soft natural lighting transitions from fresh morning, rainy afternoon, golden sunset and peaceful city night. Foreground consists of softly blurred leaves, books, coffee cups, raindrops on glass, tote bags and passing students. Midground features a modern Indonesian university campus, library, campus café, rooftop, MRT station and TransJakarta stop. Background reveals Jakarta skyline, university buildings, trees, city traffic and warm evening lights. Everything feels calm, productive, cozy and unmistakably Indonesian. Main Character Exceptionally beautiful Indonesian university student. 20 years old. Long slightly wavy black hair. Natural makeup. Warm tan skin. Oversized beige cardigan. White inner shirt. Light blue wide-leg jeans. White sneakers. Cream canvas tote bag. Silver laptop. -------------------------------------------------- SHOT 1 (0–2s) Early morning. The young woman waits at a TransJakarta bus stop. A TransJakarta bus arrives. She taps her card and boards the bus with a gentle smile. Morning sunlight shines through the windows. The camera follows naturally beside her. -------------------------------------------------- SHOT 2 (2–4s) Inside a quiet university library. She opens her laptop beside several textbooks. She writes notes while reading. Other students quietly study in the background. Soft morning light enters through large windows. The atmosphere feels peaceful and productive. -------------------------------------------------- SHOT 3 (4–6s) Campus coffee shop. A hot latte sits beside her laptop. She types her assignment while occasionally sipping coffee. Steam rises naturally from the cup. She smiles slightly after finishing a paragraph. The handheld camera gently circles around her. -------------------------------------------------- SHOT 4 (6–8s) Rain begins outside the campus. She walks beneath a transparent umbrella. Raindrops hit the pavement. Students run toward nearby buildings. She enjoys the rain while quietly smiling. The camera slowly tracks beside her. -------------------------------------------------- SHOT 5 (8–10s) Lunch break. She sits at a small bakso stall near campus. A steaming bowl of bakso is placed in front of her. She gently blows on the spoon before taking the first bite. Her face immediately lights up with a satisfied smile. The stall owner continues serving customers in the background. -------------------------------------------------- SHOT 6 (10–12s) Late afternoon. She stands on the rooftop of the university building. The Jakarta skyline glows beneath a beautiful orange sunset. A gentle breeze moves her hair. She quietly enjoys the peaceful moment while holding a cup of coffee. -------------------------------------------------- SHOT 7 (12–14s) Several close friends join her. They laugh naturally. One friend raises a smartphone. Everyone gathers together for a selfie. The camera captures genuine laughter and candid expressions. -------------------------------------------------- SHOT 8 (14–15s) Night. She rides the MRT home. Sitting beside the window, wearing wireless earbuds. Jakarta city lights pass outside. She looks out the window with a peaceful smile. The train continues moving through the city. Natural fade to black. -------------------------------------------------- Audio Morning city ambience. TransJakarta doors. Library ambience. Keyboard typing. Coffee shop sounds. Rain. Bakso stall ambience. Light wind. Friends laughing. MRT announcements. Train movement. No narration. No dialogue. No background music. -------------------------------------------------- Negative Prompt No body deformation. No facial distortion. No plastic skin. No excessive beauty filter. No CGI appearance. No hard cuts. No white flash transitions. No watermark. No logo. No subtitles. Ultra-realistic. Looks exactly like a premium cinematic university vlog filmed in Jakarta, Indonesia during 2026. Authentic Gen Z lifestyle, natural facial expressions, documentary-style handheld cinematography, emotionally immersive student life, and realistic everyday moments.

Cinematic scene

Main subject: Young Japanese woman, early 20s, natural everyday appearance, cream oversized knit cardigan over a white ribbed tank top, light blue relaxed-fit denim jeans, worn brown leather loafers, simple silver stud earrings, black shoulder-length straight hair worn loose with soft bangs. Realistic skin texture, minimal makeup, calm and thoughtful personality. Maintain consistent identity, clothing, hairstyle, and appearance throughout the entire video. Location: Authentic Japanese seaside fishing town during a quiet golden-hour evening. Narrow streets leading toward the harbor, weathered wooden homes, fishing nets drying outside, small flower pots near entrances, bicycles parked beside fences, concrete seawalls, utility poles, overhead cables, distant fishing boats, gentle ocean breeze, warm sunset light reflecting from windows. No tourist attractions, restaurants, advertisements, crowds, or commercial activity. Visual Style: Ultra-realistic observational documentary. Quiet slice-of-life storytelling with genuine human behavior. Natural pacing. Rich environmental details. Authentic everyday imperfections. Emotion conveyed through subtle expressions instead of performance. Camera Style: Late-1990s MiniDV home camcorder aesthetic. Friend or family member casually documenting ordinary life. Constant handheld movement with uneven framing, occasional accidental zoom adjustments, autofocus breathing, slight tape compression artifacts, mild interlacing, soft highlight blooming, washed-out colors, subtle chroma noise, imperfect white balance, rolling shutter, occasional dropped frames, no stabilization, no cinematic movements, no modern color grading. 00:00–00:02 Outside a weathered wooden house facing a quiet side street. She slides open the front door carrying a small watering can and gently waters potted flowers near the entrance. The camera begins recording a little too early and briefly points toward the ground before finding her. 00:02–00:04 She walks slowly toward the narrow lane leading to the harbor. A bicycle passes quietly in the background. The camera operator falls slightly behind, causing loose framing and gentle handheld sway. 00:04–00:06 She pauses beside a low seawall, watching gentle waves while seagulls fly overhead. Wind softly lifts her hair. Autofocus repeatedly shifts between her profile and the distant boats. 00:06–00:08 She bends down to pick up a smooth seashell near the shoreline and quietly examines it before smiling to herself. Warm sunlight reflects across the water as exposure subtly fluctuates. 00:08–00:10 She sits on a wooden bench overlooking the harbor, holding a warm canned tea from a convenience store purchased earlier. She quietly watches fishing boats returning while absentmindedly brushing hair behind her ear. The camera slowly drifts as if the person filming becomes distracted by the scenery. 00:10–00:12 Close side profile. Someone off-camera asks if she's ready to head home. She turns naturally, smiles with quiet warmth, nods, and softly replies, "Un." The camcorder reacts slightly late, briefly losing focus before recovering. 00:12–00:15 She walks along the seawall toward the sunset, occasionally glancing back at the camera with a genuine smile before looking ahead again. The recording abruptly stops mid-step with a brief tape glitch and cuts instantly to black. Audio: Natural ambient sound only — gentle ocean waves, distant seagulls, light wind, rustling leaves, quiet footsteps on pavement, faint boat engines far away, soft neighborhood ambience, bicycle wheels passing occasionally, fabric moving in the sea breeze. No music. No narration. No sound design. Goal: An intimate, forgotten MiniDV family recording from coastal Japan in the early 2000s—quiet, nostalgic, imperfect, deeply authentic, and emotionally understated.

Cinematic scene

Main Subject: Young Korean woman, early 20s, soft pastel cardigan over a light dress, hair in loose waves with a small flower clip, warm gentle expression. Location: Public park lined with blooming cherry blossom trees, mid-afternoon. A picnic mat spread on the grass, a small basket, petals drifting in the breeze. No crowds, no commercial elements. Visual Style: Ultra-realistic documentary realism, soft romantic candid feeling, warm dappled spring light. Camera Style: Early 2000s DV camcorder, handheld gentle drift, autofocus adjusting between her and drifting petals, soft faded pastel tones, mild grain. No stabilization. Timeline (15 sec, each slot = 2 compressed beats): 00:00–00:03 → She sits on the picnic mat, then reaches up to catch a falling petal. 00:03–00:06 → She examines it in her palm, then says to camera "이거 진짜 예쁘다" ("This is really pretty"). 00:06–00:09 → She opens the small basket, pulling out a sandwich to eat. 00:09–00:12 → A breeze scatters more petals around her; she laughs, brushing them from her hair. 00:12–00:15 → She looks at camera saying "봄이 진짜 좋다" ("I really love spring"), smiling as it fades. Audio: Wind rustling blossoms, distant birds, faint footsteps nearby, fabric rustling. Her dialogue as noted above. No music. Goal: A soft, romantic spring picnic moment gentle, warm, deeply authentic.

Cinematic scene

Main subject: young Japanese woman, early 20s, natural everyday appearance, faded sage-green sleeveless crop top, loose relaxed-fit cropped trousers, white canvas sneakers, thin gold chain necklace, black straight hair in a low messy bun with face-framing strands. Realistic skin texture, minimal makeup, soft and gentle personality. Maintain consistent identity, clothing, hairstyle, and appearance throughout the entire video. Location: Authentic Japanese residential neighborhood during a calm late morning. Narrow paved streets, low-rise wooden and stucco homes, small entryways with potted plants, bicycles leaning against walls, vending machine absent, utility poles, tangled overhead wires, mature trees casting moving shadows, quiet suburban atmosphere. No stores, advertisements, cafés, crowds, or commercial activity. Visual Style: Ultra-realistic documentary realism. Genuine candid behavior. Natural body language. Unscripted slice-of-life feeling. Strong environmental authenticity. Rich real-world details and believable human motion. Camera Style: Early-2000s consumer DV camcorder aesthetic. Friend casually recording everyday moments. Heavy handheld shake, imperfect framing, frequent autofocus hunting, lens breathing, exposure pumping when moving between sun and shade, occasional motion blur, subtle rolling shutter, mild digital compression artifacts, faded colors, soft contrast, slight sensor noise. No stabilization. No cinematic camera moves. No modern color grading. **00:00–00:02** Outside a small house entrance. She sits on a low wooden step tying her sneaker laces. A light breeze moves loose strands of hair. She smiles naturally while the camera struggles to hold focus. **00:02–00:04** The camera follows her into a narrow street lined with potted plants and low walls. She notices a stray cat approaching and crouches down. Framing drifts off-center as the operator tries to keep up. **00:04–00:06** She gently pets and feeds the cat. Autofocus repeatedly shifts between her face and the animal. Morning sunlight flickers through leaves overhead. **00:06–00:08** Small front yard beside her house. She hangs laundry on a balcony rack while fabrics sway in the breeze. Exposure changes as clouds briefly pass overhead. **00:08–00:10** On a quiet engawa (wooden porch) with a ceramic tea cup. She sits comfortably watching the neighborhood, occasionally brushing hair behind her ear. Loose handheld side angle with natural camera drift. **00:10–00:12** Close side profile. Someone off-camera greets her. She turns, raises her hand, smiles warmly, and casually says, "Ohayou." The camera catches the moment slightly late. **00:12–00:15** Walking slowly down a tree-lined residential lane holding her tea cup. She notices the camera, gives a small genuine smile, then looks away and continues walking. Recording cuts abruptly to black mid-motion as if the camcorder was switched off. Audio: Natural ambient sound only — morning birds, distant scooters, light wind, leaves rustling, faint neighborhood chatter, cat sounds, footsteps on pavement, fabric moving on a balcony rack, subtle residential ambience. No music. No sound design. No narration. Goal: Authentic Japanese neighborhood life captured like a forgotten home video from the early 2000s — candid, imperfect, realistic, warm, and deeply believable.

Cinematic scene

Create an ultra-realistic 90-second cinematic romantic comedy featuring the same young East Asian woman throughout the entire sequence. Maintain identical facial features, soft shoulder-length black hair with bangs, glowing skin, body proportions, and natural expressions in every scene. She wears a fitted white sleeveless crop top, light blue denim shorts, white sneakers, a pearl choker, delicate bracelets, rings, and carries a small white shoulder bag. Premium Korean drama aesthetic, warm natural lighting, realistic performances, cinematic handheld and gimbal camera work, shallow depth of field, soft color grading, and photorealistic 4K HDR. The film opens with the girl waking up in her cozy bedroom after hearing a notification. She excitedly reads a message on her phone from someone she recently matched with that says, "See you at 5 PM." She smiles, stretches happily, and begins getting ready. She styles her hair, applies light makeup, chooses her favorite outfit, sprays perfume, checks herself in the mirror, grabs her handbag, and leaves home feeling excited. She walks through sunny city streets toward a stylish café. Warm afternoon light fills the streets as she happily imagines meeting him for the first time. She orders an iced coffee and waits by the window. Every time the café door opens, she looks up with excitement, but each time it is someone else. Minutes pass and her smile slowly fades. Finally, she leaves the café feeling embarrassed and disappointed. As she steps outside, she accidentally bumps into a handsome young man carrying two iced coffees. One cup spills slightly onto both of them. They immediately apologize before bursting into laughter. He offers her the second untouched coffee and jokingly says, "Looks like this one was meant for you." They begin walking together through a peaceful park, talking naturally as if they've known each other for years. They laugh about funny childhood stories, feed pigeons, browse a small bookstore, share street snacks, and take playful selfies together. Their chemistry grows effortlessly while the afternoon turns into golden hour. During their walk, she casually checks her phone again and suddenly freezes. She realizes the original message actually said "Tomorrow at 5 PM." She laughs uncontrollably and shows him the screen. He laughs too before smiling warmly and saying, "Good... because otherwise we never would've met." As evening arrives, they continue walking side by side along a beautiful riverside promenade. City lights begin reflecting on the water while the sunset paints the sky orange and pink. They stop at the railing, quietly watching the skyline. He gently reaches for her hand. She smiles, accepts without hesitation, and they continue walking together toward the glowing city lights. The final cinematic shot slowly pulls back as they disappear into the sunset hand in hand, laughing together, suggesting that the best moments sometimes begin with the wrong plan. Natural ambient audio only: bedroom ambience, birds chirping, footsteps, café chatter, coffee pouring, distant traffic, park ambience, laughter, bookstore pages turning, river breeze, soft city sounds, and evening ambience. No background music, no subtitles, no logos, no watermarks, and no on-screen text. Premium Korean drama cinematography, realistic emotions, elegant camera movements, shallow depth of field, warm cinematic color grading, 16:9 widescreen, 4K HDR.

Cinematic scene

A 15-second photorealistic Korean beauty commercial for a premium cushion foundation. Use @image1 as the exact reference for the model, product, and visual style. A young Korean woman sits in a bright minimalist room with soft daylight. She looks at her reflection in the mirror, notices uneven skin, then opens a pearl-beige cushion compact. Show elegant macro shots of the cushion, puff, and smooth foundation texture. She gently taps the cushion onto her cheek and face. The skin becomes naturally fresh, luminous, and smooth while keeping realistic pores and texture. Show close-up beauty shots with soft Korean TV commercial cinematography. She walks outside under warm sunlight, looking confident and radiant. End with a premium product hero shot of the cushion compact with soft background blur. Audio: soft Korean beauty commercial music, subtle product sounds, gentle female Korean voice.

一句话了解

这个模型怎么样？

先选好输入方式、时长和分辨率，再检查工作台显示的预扣积分。生成后请播放视频，确认画面、动作和声音是否符合用途。

模型定位
Veo3.1 Quality 用于文字或首尾帧视频生成，可直接选择时长与分辨率。它不提供独立的参考图模式，模型名称也不代表每次结果都能达到某种质量。
适合谁用
可用于按文字描述制作短片，或以首帧、首尾帧安排画面的起点和终点。用于正式发布前，请检查人物、产品细节、文字、动作和声音。
本站使用说明
在视频工作台填写提示词、上传图片并选择设置；提交后可查看任务状态和积分记录。符合条件的成功结果还可继续延长或升分辨率。

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
使用位置
视频工作台
运行方式
提交后等待结果
提示词上限
5,000 字符
图片要求
JPEG／PNG · 最多 2 张 · 每张 10 MB 以内

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 Quality
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 Quality 怎么用
Veo3.1 Quality 积分
Veo3.1 Quality 和 Fast 区别
Veo3.1 Quality 和 Lite 区别
Veo3.1 Quality 支持参考图模式吗
Veo3.1 Quality 怎么延长视频
Veo3.1 Quality 怎么获取 1080p 结果
Veo3.1 Quality 怎么获取 4K 结果
Veo3.1 Quality 生成后要检查什么
Veo3.1 Quality 可以选择哪些时长和分辨率

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
先确定画面从哪里开始

只有文字构想时，描述主体、动作和场景即可。已有起始画面时上传一张首帧；需要指定结束画面时，再加一张尾帧。首尾帧用于指定画面起点和终点，不等同于角色或风格参考图。

2
需要参考图时比较其他型号

Quality 不支持参考图模式。Veo3.1 Fast 和 Lite 提供该模式，选择时请同时核对图片数量、时长、宽高比及预扣积分，不能直接沿用 Quality 的设置。

3
选好规格，再查看预扣积分

直接选择所需时长和分辨率，提交前核对预扣积分。生成后先检查视频；若还需要延长或升分辨率，再查看结果是否符合操作条件及该次操作的预扣积分。

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。

同一首帧和动作描述下，怎样比较 Quality 与 Fast 的运动、细节和声音？
需要参考图模式时，怎样核对 Quality 与 Fast 的输入方式差异？
同一目标时长和分辨率下，怎样核对 Quality 与 Lite 的预计预扣？
想延长一个成功的镜头时，怎样核对 Quality 与 Lite 的来源资格和额外预扣？
使用首尾图片制作视频时，怎样核对 Veo 3.1 Quality 与 Kling 3.0 的图片角色、上传条件及可用生成方式？
计划制作带声音的短片时，怎样核对 Veo 3.1 Quality 与 Kling 3.0 的时长和预计预扣，并检查结果是否有声音？

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。

直接生成设置
Veo3.1 Quality
可选择视频时长及 720p、1080p、4K 分辨率
Veo3.1 Fast
可选择视频时长及 720p、1080p、4K 分辨率
Veo3.1 Lite
可选择视频时长及 720p、1080p、4K 分辨率
生成方式
Veo3.1 Quality
文字、单张首帧或两张首尾帧
Veo3.1 Fast
文字、首尾帧或参考图；参考图模式另有时长与比例限制
Veo3.1 Lite
文字、首尾帧或参考图；参考图模式另有时长与比例限制
结果操作
Veo3.1 Quality
符合条件的成功结果可延长或升分辨率，另预扣积分
Veo3.1 Fast
符合条件的成功结果可延长或升分辨率，另预扣积分
Veo3.1 Lite
符合条件的成功结果可延长或升分辨率，另预扣积分
直接生成预扣积分
Veo3.1 Quality
720p／1080p／4K：225／233／285 积分
Veo3.1 Fast
720p／1080p／4K：30／38／90 积分
Veo3.1 Lite
720p／1080p／4K：15／23／75 积分
比较时先看
Veo3.1 Quality
输入方式、所选分辨率与预扣积分
Veo3.1 Fast
是否需要参考图，以及所选分辨率的预扣积分
Kling 3.0
在详情页核对输入方式、时长和积分

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。

模型名称不能替代结果检查

Quality 的名称和积分价格不能保证人物、文字、动作或声音一定符合要求。请按实际用途检查视频，关键细节尤其需要逐一确认。

直接生成与结果操作分开计费

选择 1080p 或 4K 直接生成，使用该分辨率的预扣积分；对符合条件的已有结果获取 1080p 或 4K，是另一次操作。两者的使用条件和预扣积分不同。

能力详解

文字、首帧与首尾帧

文字生成不需要图片。图生视频使用单张首帧或两张首尾帧，最多 2 张 JPEG 或 PNG，每张不超过 10 MB。Quality 不接受参考图模式。

延长与升分辨率

延长仅适用于你本人已成功的 Quality 基础生成结果。获取 1080p 或 4K 仅适用于你本人已成功的 Quality 720p 基础结果或延长结果，不能从已升分辨率的结果重复发起。每项操作另预扣积分。

可选时长与分辨率

视频时长可选 4、6、8 秒，分辨率可选 720p、1080p、4K。宽高比支持 16:9、9:16 和 Auto；也可填写水印文本，选择自动翻译提示词或保留原文。

适合做什么

用文字描述短片

写清主体、场景、动作和镜头，再选择时长与分辨率。生成后检查实际画面和声音；涉及人物、产品或可读文字时，逐一核对关键细节。

从首帧过渡到尾帧

用单张图片指定起始画面，或用两张图片指定起始和结束画面。确认上传顺序，在提示词中描述中间的动作；首尾帧之间的过渡效果仍需查看结果。

继续处理已有结果

已有成功的基础结果时，可按条件继续延长；720p 基础结果或成功的延长结果可按条件获取 1080p、4K。操作前核对另行预扣的积分，完成后再检查新结果。

提示词技巧

先写清主体和动作

说明谁在什么场景里做什么，再补充镜头和需要保留的细节。比较模型时，尽量使用相同素材和提示词；规格不能对齐时，记录差异，不把一次结果当成固定优劣。

说明首尾帧之间如何变化

首帧和尾帧表示画面的起点与终点。在提示词中写清希望出现的动作或过渡，不把两张图片当成独立的角色、产品或风格参考图。

操作后重新播放视频

延长或升分辨率完成后，重新检查画面、动作衔接和声音，并查看这次操作的积分状态。分辨率变化不保证细节或内容一定更好。

为什么选它

可用文字生成，也可用单张首帧或两张首尾帧。
可直接选择视频时长与 720p、1080p、4K 分辨率。
符合条件的成功结果可继续延长或升分辨率。
直接生成与结果操作分别预扣积分，确认用量后结算。

使用前要知道

人物、产品细节、文字、动作与声音都需要查看实际结果，不能由模型名称保证。
Quality 不提供独立的参考图模式，首尾帧不能替代该模式。
结果操作受归属、任务状态、来源和分辨率条件限制；直接生成的 1080p、4K 结果不能再发起升分辨率操作。
生成成功不代表积分已确认结算；用量尚未确认时仍保留预扣，请查看积分状态。

可调参数

根据这些信息，判断模型是否适合你的任务。

生成方式
可选
参数类型: 选择项
无图时使用文字；上传图片后使用首帧或首尾帧
文字生成视频
首帧或首尾帧生成视频
宽高比
可选
参数类型: 选择项
默认：16:9
横向（16:9）
竖向（9:16）
自动裁切（Auto）
分辨率
可选
参数类型: 选择项
默认：720p
720p — 预扣 225 积分
1080p — 预扣 233 积分
4K — 预扣 285 积分
视频时长
可选
参数类型: 选择项
默认：8 秒
4 秒
6 秒
8 秒
水印文本
可选
参数类型: 文本
提示词翻译
可选
参数类型: 选择项
默认：自动翻译为英文
自动翻译为英文
保留原文

积分消耗

720p／1080p／4K 分别预扣 225／233／285 积分

直接生成 720p、1080p、4K 分别预扣 225、233、285 积分。延长预扣 225 积分；符合条件的 1080p、4K 结果操作分别另预扣 8、60 积分。确认实际用量后结算；生成成功但用量尚未确认时保留预扣，并提示本次消耗尚未确认。

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 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。

AI 视频模型
预计 30～90 积分
查看详情立即使用

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

Kling 3.0

用文字或图片制作视频，可选择单镜头，也可逐镜头安排提示词与时长。声音和画质档位会参与预计预扣计算；人物、口型、文字、声音及镜头衔接都需检查实际结果。

AI 视频模型
预计预扣 42～1,005 积分／次
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 Google Cloud 的 Veo 模型资料、在线预测接口参考和更新信息，用于说明官方背景。Quality 在 Kyeo AI 的输入方式、直接生成与结果操作条件依据本站当前设置；官方提供的参考图能力或服务安排不自动成为本站此型号的功能。实际视频和最终消耗仍需按结果与费用确认记录核对。

内容复核日期: 2026-08-28
Google Cloud：Veo 3.1 模型资料
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

这些链接提供 Google 的模型资料与更新信息；在 Kyeo AI 使用时，请按本页说明和工作台可选设置操作。

查看原始来源