ByteDance 的 SD 2 Immagine a Video(Fast)。以更低成本快速将首帧图像制作成视频,支持 4–15 秒时长。
About this model
SD 2 Immagine a Video(Fast)使用 ByteDance 的 SD 2 模型,以更低成本快速将参考图像制作成视频。它使用所提供的图像作为开场帧,并生成 4–15 秒的视频。
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.15 per second (e.g. $0.75 for 5 seconds) | Fatturazione al secondo di video generato. |
| Fal.ai | $0.3024/sec (high) / $0.2419/sec (basic) | Fal.ai charges $0.3024/sec for high quality and $0.2419/sec for basic. muapiapp Fast at $0.15/sec is 50% cheaper than Fal.ai's basic rate. |
| Replicate | $0.3024/sec (high) / $0.2419/sec (basic) | Replicate charges the same as Fal.ai — $0.3024/sec (high), $0.2419/sec (basic). muapiapp Fast at $0.15/sec is 50% cheaper than Replicate's basic rate. |
Fatturazione al secondo di video generato.
Fal.ai charges $0.3024/sec for high quality and $0.2419/sec for basic. muapiapp Fast at $0.15/sec is 50% cheaper than Fal.ai's basic rate.
Replicate charges the same as Fal.ai — $0.3024/sec (high), $0.2419/sec (basic). muapiapp Fast at $0.15/sec is 50% cheaper than Replicate's basic rate.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | 指导Video动画的文本描述。使用 @character:<id> 引用已完成的 Seedance 2 Character 生成结果。 | The person walks forward with a smile. |
| 参考Immagine | array | 1 张Immagine将作为首帧(first_last_frames 模式);2–9 张Immagine会切换到 omni_reference 模式,请在Prompt中使用 @image1、@image2 等进行引用。 | https://d3adwkbyhxyrtq.cloudfront.net/ai-images/186/712345784292/4a8c5c70-abcc-4920-873e-b0e219986453.jpg |
| Proporzioni | Enum (6 options) | OutputVideo的Proporzioni。 | 16:9 |
| Durata (secondi)(秒) | int | VideoDurata(秒)。 | 5 |
指导Video动画的文本描述。使用 @character:<id> 引用已完成的 Seedance 2 Character 生成结果。
The person walks forward with a smile.1 张Immagine将作为首帧(first_last_frames 模式);2–9 张Immagine会切换到 omni_reference 模式,请在Prompt中使用 @image1、@image2 等进行引用。
https://d3adwkbyhxyrtq.cloudfront.net/ai-images/186/712345784292/4a8c5c70-abcc-4920-873e-b0e219986453.jpgOutputVideo的Proporzioni。
16:9VideoDurata(秒)。
5Developer documentation
上传图像:通过 images_list 提供 JPEG、PNG 或 WebP 图像。
编写Prompt:描述所需的运动和动画效果。
设置时长:设置为 4 到 15 秒。
提交并轮询:使用返回的 request_id 轮询结果。
Frequently asked
支持 JPEG、PNG 和 WebP。
不可以——OutputProporzioni会根据Input图像的尺寸自动确定。
Fast 模型采用更轻量的推理流程,比 Pro 更快、更便宜,但Output细节会略有减少。