图生视频 API

面向开发者的 AI API

图生视频 API

通过 PoYo 图生视频 API,为产品照片、肖像和插画增加动态效果。对比首帧保持、运镜、时长、音频与价格,构建参考图驱动的视频工作流。

匹配模型

46 个模型

MiniMax H3 / Hailuo 03
图像生成视频

$0.105 /秒

hailuo-03

MiniMax H3 (Hailuo 03) generates native 2K video from text, first/last frames, or image, video, and audio references.

Seedance 2.5
图像生成视频

$0.085 /计费秒

seedance-2.5

ByteDance Seedance 2.5 video generation with 4-30 second output, first and last frame control, up to 50 image, video, and audio references, optional synchronized audio, and 480p, 720p, or 1080p delivery.

FLUX 3
图像生成视频

$0.17 /秒

flux-3/text-to-video

Black Forest Labs' FLUX 3 video family for text, images, first and last frames, source-video extension, positioned keyframes, and native audio generation.

Seedance 2
图像生成视频

$0.045 /输出与参考视频秒

seedance-2

ByteDance Seedance 2 video generation with text-to-video, image-to-video, multimodal reference-to-video, video-to-video, and audio-to-video workflows using image, video, and audio references with optional native audio.

Gemini Omni 1.1 Flash
图像生成视频

$0.225 /次生成

gemini-omni-1.1-flash

Gemini Omni 1.1 Flash API for text-to-video, first and last frame interpolation, reference image generation, and reference-video workflows.

Gemini Omni 1.2 Flash
图像生成视频

$0.027 /秒

gemini-omni-1.2-flash

Gemini Omni 1.2 Flash API on PoYo. Generate 3–15 second videos at 360p to 4K from text, first and last frames, or up to 10 reference images and 3 reference videos, and edit existing videos up to 15 seconds. From 5.46 credits ($0.0273) per second.

Seedance 2.0 Mini
图像生成视频

$0.03 /输出与参考视频秒

seedance-2-mini

ByteDance Seedance 2.0 Mini video generation for lower-cost text-to-video, image-to-video, and multimodal reference workflows with 480p and 720p output.

FLUX 3 Max
图像生成视频

$0.17 /秒

flux-3-max/text-to-video

Create 5–20 second videos with FLUX 3 Max from text, one or two images, or up to ten positioned keyframes. Choose 720p or 1080p and generate native synchronized audio.

Kling 3.0 Motion Control
图像生成视频

$0.045 /秒

kling-3.0-motion-control

Kling 3.0 Motion Control is a reference-driven motion transfer model that combines one character image and one source video with transparent per-second pricing.

Happy Horse 1.1
图像生成视频

$0.11 /秒

happy-horse-1.1

Alibaba Happy Horse 1.1 video generation with text-to-video, image-to-video, and reference-to-video workflows.

Kling 3.0
图像生成视频

$0.135 /秒

kling-3.0/standard

Kuaishou's advanced Kling 3.0 video model family with Standard, Pro, and native 4K generation, multi-shot storyboarding, synchronized audio, and element-based consistency.

Kling O3
图像生成视频

$0.05 /秒

kling-o3/standard

Kling O3 video generation on PoYo with Standard, Pro, and 4K variants for text-to-video, image-to-video, and reference-to-video workflows.

Sora 2 Official
图像生成视频

$0.20 /条视频

sora-2-official

OpenAI Sora 2 on PoYo with synced audio, improved physics, optional reference image input, and fixed 4-second, 8-second, 12-second, 16-second, and 20-second tiers.

Wan 2.7 Video
图像生成视频

$0.06 /秒

wan2.7-text-to-video

Wan 2.7 Video models on PoYo for text-to-video, image-to-video, reference-to-video, and edit-video workflows.

PixVerse V6 Max
图像生成视频

$0.024 /秒

pixverse-v6-max

PixVerse V6 Max API on PoYo. Generate 1–15 second videos from text or one image at 360p to 1080p, with optional native dialogue, music and sound effects. From 4.8 credits ($0.024) per second.

Vidu Q4
图像生成视频

$0.045 /秒

vidu-q4

Vidu Q4 API on PoYo. Turn a start image or up to 12 reference images and 3 voice clips into 3-16 second cinematic videos with native audio, multi-shot storytelling and 540p to 4K output. From 9 credits ($0.045) per second.

Wan 3.0
图像生成视频

$0.05 /计费秒

wan3.0-text-to-video

Generate videos up to 30 seconds with Wan 3.0 using text, first and last frames, or multimodal references including images, video, audio, documents, and links.

Wan 3.0 Video Prime
图像生成视频

$0.068 /计费秒

wan3.0-prime-text-to-video

Wan 3.0 Video Prime is Alibaba's Wan 3.0 tier optimized for faster turnaround, with multimodal image, video, audio, document, and public webpage references, videos up to 30 seconds, and optional generated audio.

OmniHuman 2.0
图像生成视频

$0.105 /秒

omnihuman-2.0

OmniHuman 2.0 API on PoYo. Animate one portrait with 4-300 seconds of speech or singing into a 720p talking video with precise lip-sync, natural emotion, gestures and multi-person scenes. 21 credits ($0.105) per output second.

Wan Animate 2
图像生成视频

即将上线

Wan Animate 2

Alibaba's end-to-end character animation model for direct motion transfer, identity preservation, and text-driven viewpoint control. Coming soon to PoYo.

Kling 4.0
图像生成视频

$0.085 /计费秒

kling-4.0

Kling 4.0 API on PoYo. Generate 3–30 second videos from text, first and last frames, or image/video references and subjects. Edit source videos at 720p or 1080p.

Kling 4.0 Flash
图像生成视频

$0.063 /计费秒

kling-4.0-flash

Kling 4.0 Flash API on PoYo. Generate fast 3–20 second 720p videos from text, a start frame, or image/video references and subjects, and edit source videos with references.

MiniMax H3 Max
图像生成视频

$0.05 /秒

h3-max

MiniMax H3 Max generates 5–15 second videos from text, first/last frames, or image, video and audio references at 480p, 768p and 1080p.

MiniMax H3 Max Turbo
图像生成视频

$0.025 /秒

h3-max-turbo

MiniMax H3 Max Turbo generates 5–15 second videos from text or first/last frames at 480p, 768p and 1080p.

Seedance 2.5 Flash
图像生成视频

$0.058 /计费秒

seedance-2.5-flash

ByteDance Seedance 2.5 Flash, the faster, lower-cost tier of Seedance 2.5: up to 30-second 480p or 720p videos with synchronized audio from text, first and last frames, or image, video, and audio references.

Grok Imagine
图像生成视频

$0.03 /张

grok-imagine-image

xAI's Aurora-powered visual AI for image generation and video creation with Fun, Normal, and Spicy creative modes.

Hailuo 02
图像生成视频

$0.035 /秒

hailuo-02

MiniMax's #2 globally-ranked video model with NCR architecture, ultra-realistic physics, and 1080p cinematic output.

Veo 3.1
图像生成视频

$0.10 /条视频

veo3.1-lite

Google DeepMind's VEO 3.1 video family with text-to-video, image-to-video, 720p, 1080p, and 4K output options.

Veo 3.1 Official
图像生成视频

$0.018 /秒

veo3.1-fast-official

Official VEO 3.1 video generation with text, image, first/last-frame and reference workflows across fast, lite and quality tiers.

Wan 2.2 Fast
图像生成视频

$0.03 /次生成

wan2.2-image-to-video-fast

Wan 2.2 Fast provides fast text-to-video and image-to-video generation with low-cost 480p and 720p tiers for quick iteration.

Grok Imagine Video 1.5
图像生成视频

$0.072 /秒

grok-imagine-video-1.5

Grok Imagine Video 1.5 API for text-to-video, single-frame image-to-video, and 1–7 image reference-to-video generation with up to 1080p output.

Hailuo 2.3
图像生成视频

$0.175 /条视频

hailuo-2.3

MiniMax's Hailuo 2.3 video model for realistic human motion, expressive characters, and text-to-video or first-frame guided generation at 768p and 1080p.

Omni Flash
图像生成视频

$0.60 /次生成

omni-flash

Omni Flash API access for text-to-video, image-to-video, three-image reference fusion, and video-input generation workflows.

Seedance 1.0 Pro
图像生成视频

$0.105 /条视频

seedance-1.0-pro

ByteDance's #1 ranked video model with multi-shot storytelling, cinema-grade motion, and bilingual text-to-video generation.

Seedance 1.5 Pro
图像生成视频

$0.045 /条视频

seedance-1.5-pro

ByteDance's latest video model with synchronized audio generation, flexible aspect ratios, and enhanced motion control.

Wan 2.5
图像生成视频

$0.15 /条视频

wan2.5-image-to-video

Wan 2.5 combines text-to-video and image-to-video generation with 5-second and 10-second output, synchronized audio support, and multiple size and resolution tiers.

Kling 1.6
图像生成视频

$0.045 /秒

kling-1.6/standard

Kling 1.6 Standard and Pro video generation on PoYo with text, first/last frame, and multi-image element reference workflows.

Kling 2.1
图像生成视频

$0.15 /条视频

kling-2.1/standard

Kling 2.1 on PoYo provides Standard and Pro image-to-video modes with 5-second and 10-second clips, start-frame control, and optional end-frame control in Pro.

Kling 2.6
图像生成视频

$0.325 /条视频

kling-2.6

Kuaishou's revolutionary video model that simultaneously generates visuals with synchronized dialogue, sound effects, and ambient audio in one pass.

Kling Avatar 2.0
图像生成视频

$0.035 /秒

kling-avatar-2.0/standard

Kling Avatar 2.0 creates audio-driven talking avatar videos from one reference image and one driving audio file, with Standard and Pro quality modes.

Wan 2.6
图像生成视频

$0.40 /条视频

wan2.6-text-to-video

Alibaba's Wan 2.6 video generation family for text-to-video, image-to-video, and video-to-video with multi-shot 1080p output.

Kling 2.5 Turbo Pro
图像生成视频

$0.21 /条视频

kling-2.5-turbo-pro

Kling 2.5 Turbo Pro is a flexible short-form video model with text-to-video, optional frame guidance, smooth motion, cinematic depth, and fixed 5-second and 10-second tiers.

Kling 3.0 Turbo
图像生成视频

$0.085 /秒

kling-3.0-turbo/standard

Kling 3.0 Turbo is the speed-optimized Kling 3.0 variant for high-volume text-to-video and image-to-video generation with multi-shot storyboarding. Standard (720p) and Pro (1080p) models available.

Wan Animate
图像生成视频

$0.035 /秒

wan-animate-move

Alibaba's 14B-parameter character animation model that transfers motion from reference videos to static characters with exceptional identity preservation.

Kling 2.6 Motion Control
图像生成视频

$0.04 /秒

kling-2.6-motion-control

Kuaishou's motion control model that transfers motion from reference videos to character images while maintaining identity and adapting environments.

Happy Horse
图像生成视频

$0.08 /秒

happy-horse

Alibaba Happy Horse 1.0 video generation and editing with text-to-video, image-to-video, reference-to-video, and video-edit workflows.

图像生成视频模型 API - 价格和模型适配

选择模型前,对比供应商、支持的输入、输出格式和价格。

精确任务匹配

只有模型目录元数据包含 Image to Video 的模型才会出现在这里。

供应商对比

无需离开任务目录,即可查看不同供应商的模型系列。

API 就绪路径

每张模型卡都会跳转到 PoYo 的价格、示例、Playground 控件和 API 详情。

模型供应商任务类型价格
MiniMax H3 / Hailuo 03

hailuo-03

MiniMaxText to Video, Image to Video, Reference to Video$0.105/秒
Seedance 2.5

seedance-2.5

SeedanceText to Video, Image to Video, Video to Video$0.085/计费秒
FLUX 3

flux-3/text-to-video

Black Forest LabsText to Video, Image to Video$0.17/秒
Seedance 2

seedance-2

SeedanceText to Video, Image to Video, Video to Video$0.045/输出与参考视频秒
Gemini Omni 1.1 Flash

gemini-omni-1.1-flash

GoogleText to Video, Image to Video, Video to Video$0.225/次生成
Gemini Omni 1.2 Flash

gemini-omni-1.2-flash

GoogleText to Video, Image to Video, Reference to Video$0.027/秒
Seedance 2.0 Mini

seedance-2-mini

SeedanceText to Video, Image to Video, Video to Video$0.03/输出与参考视频秒
FLUX 3 Max

flux-3-max/text-to-video

Black Forest LabsText to Video, Image to Video$0.17/秒
Kling 3.0 Motion Control

kling-3.0-motion-control

KlingMotion Control, Image to Video$0.045/秒
Happy Horse 1.1

happy-horse-1.1

AlibabaText to Video, Image to Video, Reference to Video$0.11/秒
Kling 3.0

kling-3.0/standard

KlingText to Video, Image to Video$0.135/秒
Kling O3

kling-o3/standard

KlingText to Video, Image to Video, Reference to Video$0.05/秒
Sora 2 Official

sora-2-official

OpenAIText to Video, Image to Video$0.20/条视频
Wan 2.7 Video

wan2.7-text-to-video

AlibabaText to Video, Image to Video, Video to Video$0.06/秒
PixVerse V6 Max

pixverse-v6-max

PixVerseText to Video, Image to Video$0.024/秒
Vidu Q4

vidu-q4

ViduImage to Video, Reference to Video$0.045/秒
Wan 3.0

wan3.0-text-to-video

AlibabaText to Video, Image to Video, Reference to Video$0.05/计费秒
Wan 3.0 Video Prime

wan3.0-prime-text-to-video

AlibabaText to Video, Image to Video, Reference to Video$0.068/计费秒
OmniHuman 2.0

omnihuman-2.0

ByteDanceImage to Video, Audio to Video, Talking Avatar$0.105/秒
Wan Animate 2

wan-animate-2

AlibabaImage to Video即将上线
Kling 4.0

kling-4.0

KlingText to Video, Image to Video, Reference to Video$0.085/计费秒
Kling 4.0 Flash

kling-4.0-flash

KlingText to Video, Image to Video, Reference to Video$0.063/计费秒
MiniMax H3 Max

h3-max

MiniMaxText to Video, Image to Video, Reference to Video$0.05/秒
MiniMax H3 Max Turbo

h3-max-turbo

MiniMaxText to Video, Image to Video$0.025/秒
Seedance 2.5 Flash

seedance-2.5-flash

SeedanceText to Video, Image to Video, Video to Video$0.058/计费秒
Grok Imagine

grok-imagine-image

xAIText to Image, Image to Video, Uncensored$0.03/张
Hailuo 02

hailuo-02

MiniMaxText to Video, Image to Video$0.035/秒
Veo 3.1

veo3.1-lite

GoogleText to Video, Image to Video$0.10/条视频
Veo 3.1 Official

veo3.1-fast-official

GoogleText to Video, Image to Video$0.018/秒
Wan 2.2 Fast

wan2.2-image-to-video-fast

AlibabaText to Video, Image to Video$0.03/次生成
Grok Imagine Video 1.5

grok-imagine-video-1.5

xAIImage to Video, Reference to Video$0.072/秒
Hailuo 2.3

hailuo-2.3

MiniMaxText to Video, Image to Video$0.175/条视频
Omni Flash

omni-flash

GoogleText to Video, Image to Video, Video to Video$0.60/次生成
Seedance 1.0 Pro

seedance-1.0-pro

SeedanceText to Video, Image to Video$0.105/条视频
Seedance 1.5 Pro

seedance-1.5-pro

SeedanceText to Video, Image to Video$0.045/条视频
Wan 2.5

wan2.5-image-to-video

AlibabaText to Video, Image to Video$0.15/条视频
Kling 1.6

kling-1.6/standard

KlingText to Video, Image to Video$0.045/秒
Kling 2.1

kling-2.1/standard

KlingImage to Video$0.15/条视频
Kling 2.6

kling-2.6

KlingText to Video, Image to Video$0.325/条视频
Kling Avatar 2.0

kling-avatar-2.0/standard

KlingImage to Video, Audio to Video, Talking Avatar$0.035/秒
Wan 2.6

wan2.6-text-to-video

AlibabaText to Video, Image to Video, Video to Video$0.40/条视频
Kling 2.5 Turbo Pro

kling-2.5-turbo-pro

KlingText to Video, Image to Video$0.21/条视频
Kling 3.0 Turbo

kling-3.0-turbo/standard

KlingText to Video, Image to Video$0.085/秒
Wan Animate

wan-animate-move

AlibabaImage to Video$0.035/秒
Kling 2.6 Motion Control

kling-2.6-motion-control

KlingImage to Video, Motion Control$0.04/秒
Happy Horse

happy-horse

AlibabaText to Video, Image to Video, Video to Video$0.08/秒

常见问题

什么是图生视频 API?

+

图生视频 API 使用静态图片作为视频起点或视觉参考,结合动作提示词与模型支持的设置生成新片段。它不是简单的幻灯片,也不保证逐帧完全还原原图细节。

什么图片更适合图生视频?

+

选择主体清楚、细节可见、构图合理的清晰图片,并为预期动作留出空间。产品标签和边缘应易于辨认,人物脸部应清楚,尽量避免严重压缩和复杂遮挡。

图生视频提示词怎么写?

+

重点说明什么需要移动、什么需要保持稳定,描述主体动作、镜头和氛围,无需重复图片中的所有细节。先测试简单动作,检查结果后每次调整一项指令。

可以同时提供首帧和尾帧吗?

+

部分接口支持首尾帧,其他接口可能只支持起始图片或不同参考模式。先核对字段和图片数量,选择能合理过渡的两张图;主体或构图差异过大会增加生成难度。

为什么人物、产品或标志会变形?

+

模型从有限图片推断新视角和运动,细节可能漂移。可使用更清晰的图片、减小动作幅度,并明确保留主体。用同一素材比较模型,发布前检查重要品牌细节。

可以通过图生视频 API 控制运镜吗?

+

可在提示词中描述镜头行为,部分模型另有专门控制。只使用接口已支持的设置,先指定一种清晰运镜,例如缓慢推进或平移,同时检查主体是否保持稳定。

生成的视频可以带声音吗?

+

音频支持因模型而异,可能为原生音频、可选音频或静音输出。口播人物可比较数字人模型,需要准确旁白时可增加独立文本转语音步骤,并核对相关价格。

如何选择时长、分辨率和比例?

+

使用模型文档列出的值,并让来源图片构图适合最终画面比例。长时长和高分辨率会影响费用与生成表现,建议先用合适的草稿设置测试,再批量生产。

提交图片后如何获取视频?

+

按文档提交模型与图片输入,保存 task_id,通过状态查询或支持的 callback_url 获取完成结果。保留原图和请求设置,便于比较版本与重新生成。

图生视频 API 一次请求多少钱?

+

查看模型计费单位,可能按片段、生成次数或秒数计算,分辨率、时长、质量和音频会影响档位。根据完整配置和预期尝试次数估算,不要将起始价套用到所有视频。

图生视频、动作控制和数字人如何选择?

+

静态图片增加动作选图生视频;让角色跟随参考视频表演选动作控制;让人像根据音频说话选数字人。输出可能相似,但所需输入和控制方式不同。

自动化图生视频前需要检查什么?

+

检查图片 URL、格式、裁剪、时长和模型 ID,保存任务并控制并发。先用少量代表性素材评估主体保持和实际成本,遇到超时先查询原任务再决定重试。