Create Video Generation Task

This interface is designed to integrate the generation function interfaces provided by various deployment parties, extracting commonly used parameter fields and response fields, standardizing field naming and parameter/response data formats, and improving efficiency.
The interface supports parameter transmission in both form-data and JSON formats.
This interface focuses solely on obtaining the task_id. For other information, you can query via the data field.

Price: Charged based on the corresponding video model.

模型列表

Model name	Description	302ai Original Document Link
stable_diffusion	Generate a short video based on an initial image using Stable Video Diffusion.	https://302ai-en.apifox.cn/api-207705235
luma_video	Text/Image-to-video generation from Luma AI: Generates a 5-second video based on text or images. Supports specifying the first and last frame for connection.	https://302ai-en.apifox.cn/api-207705237
runway_gen3_t2v	Text-to-video generation from Runway Gen-3: Generates a 10-second video based on text.	https://302ai-en.apifox.cn/api-207705240
runway_gen3_i2v	Image-to-video generation from Runway Gen-3: Generates a 10-second video based on images.	https://302ai-en.apifox.cn/api-207705241
runway_gen3_v2v	Video-to-Video Generation from Runway Gen-3: Transforms the original video into different styles based on the video and prompt.	https://302ai-en.apifox.cn/api-207705241
runway_gen3_i2v_turbo	Fast Image-to-Video Generation from Runway Gen-3-Turbo: Generates 5 or 10-second videos from images in one go. API format updated on 2024/10/10 to support keyframe generation.	https://302ai-en.apifox.cn/api-224541525
runway_gen3_v2v_turbo	Fast Video-to-Video Generation from Runway Gen-3-Turbo.	https://302ai-en.apifox.cn/api-224541525
runway_gen3_v2v_turbo	Fast Video-to-Video Generation from Runway Gen-3-Turbo.	https://302ai-en.apifox.cn/api-224541525
kling_10_t2v	Text-to-Video Generation from Kling: Uses the kling-1.0 model.	https://302ai-en.apifox.cn/api-207705249
kling_15_t2v_hq	Text-to-Video Generation from Kling: Uses the kling-1.5 model.	https://302ai-en.apifox.cn/api-207705248
kling_16_t2v	Text-to-Video Generation from Kling: Uses the kling-1.6 model.	https://302ai-en.apifox.cn/api-207705245
kling_16_t2v_hq	Text-to-Video Generation from Kling: Uses the kling-1.6 HD model.	https://302ai-en.apifox.cn/api-207705247
kling_10_i2v	Image-to-Video Generation from Kling: Uses the kling-1.0 model.	https://302ai-en.apifox.cn/api-238109409
kling_15_i2v	Image-to-Video Generation from Kling: Uses the kling-1.5 model.	https://302ai-en.apifox.cn/api-238109409
kling_15_i2v_hq	Image-to-Video Generation from Kling: Uses the kling-1.5 HD model.	https://302ai-en.apifox.cn/api-207705248
kling_16_i2v	Image-to-Video Generation from Kling: Uses the kling-1.6 model.	https://302ai-en.apifox.cn/api-246824589
kling_16_i2v_hq	Image-to-Video Generation from Kling: Uses the kling-1.6 HD model.	https://302ai-en.apifox.cn/api-246824653
cog_t2v	Text-to-Video Model from Zhipu.	https://302ai-en.apifox.cn/api-261643423
cog_i2v	Image-to-Video Model from Zhipu	https://302ai-en.apifox.cn/api-261643424
minimaxi_T2V-01	Text-to-Video Model from Minimax	https://302ai-en.apifox.cn/api-267624009
minimaxi_T2V-01-Director	Text-to-Video Model from Minimax.	https://302ai-en.apifox.cn/api-222607630
minimaxi_I2V-01	Image-to-Video Model from Minimax	https://302ai-en.apifox.cn/api-222607630
minimaxi_I2V-01-live	Image-to-Video Model from Minimax.	https://302ai-en.apifox.cn/api-222607630
minimaxi_I2V-01-Director	Image-to-Video Model from Minimax	https://302ai-en.apifox.cn/api-222607630
minimaxi_S2V-01	Subject Generation Video Model from Minimax.	https://302ai-en.apifox.cn/api-256735121
pika_1.0	Image/Text-to-Video Model from Pika: Uses the 1.0 version model.	https://302ai-en.apifox.cn/api-225990812
pika_1.5	Image/Text-to-Video Model from Pika: Uses the 1.5 version model	https://302ai-en.apifox.cn/api-225990812
pika_2.0	Image/Text-to-Video Model from Pika: Uses the 2.0 version model.	https://302ai-en.apifox.cn/api-225990812
pika_2.0-contextualize	Reference Subject Generation Video Model from Pika.	https://302ai-en.apifox.cn/api-252684965
pixverse_v2	Image-to-Video Functionality from Pixverse: Uses the V2 version.	https://302ai-en.apifox.cn/api-236444989
pixverse_v3	Image-to-Video Functionality from Pixverse: Uses the V3 version.	https://302ai-en.apifox.cn/api-236444989
pixverse_v3.5	Image-to-Video Functionality from Pixverse: Uses the V3.5 version	https://302ai-en.apifox.cn/api-236444989
pixverse_v4	Image-to-Video Functionality from Pixverse: Uses the V4 version.	https://302ai-en.apifox.cn/api-236444989
genmo_t2v	Genmo's Latest Open-Source Video Generation Model Mochi1: Sets a new benchmark in video generation. Mochi1 adopts the innovative Asymmetric Diffusion Transformer (AsymmDiT) architecture.	https://302ai-en.apifox.cn/api-256081480
haiper_20_t2v	Emerging Video Generation Company from London: Offers the 2.0 version text-to-video functionality.	https://302ai-en.apifox.cn/api-232137062
haiper_20_i2v	Emerging Video Generation Company from London: Offers the 2.0 version image-to-video functionality.	https://302ai-en.apifox.cn/api-232137063
haiper_25_t2v	Emerging Video Generation Company from London: Offers the 2.5 version text-to-video functionality	https://302ai-en.apifox.cn/api-263666434
haiper_20_i2v	Emerging Video Generation Company from London: Offers the 2.5 version image-to-video functionality.	https://302ai-en.apifox.cn/api-263666435
ltx_t2v	Open-Source Text-to-Video Model: Features ultra-fast generation speed. Note: Detailed prompts are essential for good results, otherwise the quality may be poor.	https://302ai-en.apifox.cn/api-237132298
ltx_i2v	Open-Source Image-to-Video Model: Features ultra-fast generation speed. Note: Images must have a 3:2 aspect ratio; otherwise, they will be stretched.	https://302ai-en.apifox.cn/api-237132298
wanx2.1-t2v-turbo	Tongyi Wanxiang Official Model: Features faster generation speed with balanced performance.	https://302ai-en.apifox.cn/api-254095110
wanx2.1-t2v-plus	Tongyi Wanxiang Official Model: Features richer details and more textured visuals.	https://302ai-en.apifox.cn/api-254095110
302wan_t2v	Open-Source Text-to-Video Model.	https://302ai-en.apifox.cn/api-265218437
302wan_i2v	Open-Source Image-to-Video Model.	https://302ai-en.apifox.cn/api-265218439
seaweed_t2v	Text-to-Video Model from Jimeng.	https://302ai-en.apifox.cn/api-256341887
seaweed_i2v	Image-to-Video Model from Jimeng: Supports only 5-second durations	https://302ai-en.apifox.cn/api-256341887
siliconflow_ltx	LTX Model Deployed by Silicon-Based Flow.	https://302ai-en.apifox.cn/api-255033894
siliconflow_hunyuan	Hunyuan Model Deployed by Silicon-Based Flow.	https://302ai-en.apifox.cn/api-255033895
siliconflow_mochi	Mochi Model Deployed by Silicon-Based Flow.	https://302ai-en.apifox.cn/api-255033896
google_veo_t2v	Google's Latest Text-to-Video Model.	https://302ai-en.apifox.cn/api-263672348
skyreels_i2v	Kunlun Wanwei's Latest Image-to-Video Model.	https://302ai-en.apifox.cn/api-263672450
higgsfield_turbo_i2v	The image-to-text model from higgsfield.ai indicates that the "prompt" parameter is less effective for generating videos compared to the "motions" parameter. It is recommended to explicitly specify the "motions" parameter. If not provided, the system will use a random value, which may result in video output that does not meet expectations	https://302ai-en.apifox.cn/api-294543776
higgsfield_lite_i2v	The image-to-text model from higgsfield.ai suggests that the "prompt" parameter is less effective for video generation than the "motions" parameter. It is advisable to specify the "motions" parameter explicitly. If left unspecified, the system will use a random value, potentially leading to suboptimal video results	https://302ai-en.apifox.cn/api-294543776
higgsfield_standard_i2v	The image-to-text model from higgsfield.ai highlights that the "prompt" parameter performs worse in video generation compared to the "motions" parameter. It is best to input a specified "motions" parameter. If omitted, the system will default to a random value, possibly resulting in unsatisfactory video output	https://302ai-en.apifox.cn/api-294543776

Request

Header Params

Authorization

string

optional

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

prompt

string

提示词

optional

Text-to-Video Model is Required

image

string

首帧/主体图片

optional

Supports formfile (when using form-data for parameter transmission) / accessible public links / base64 images (starting with data:image).

end_image

string

尾帧图片

optional

Supports formfile (when using form-data for parameter transmission) / accessible public links / base64 images (starting with data:image).

video

string

视频

optional

Supports formfile (when using form-data for parameter transmission) / accessible public links / base64 videos (starting with data:image).

fps

视频帧率

optional

For specific optional parameter values, refer to the original interface documentation.

Any of

integer

string

duration

integer

视频时长

optional

model

string

模型

required

Refer to the table in the documentation for details.

Example

{
  "prompt": "a dog is running",
  "model": "luma_video"
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

application/json

Body

task_id

string

任务id

required

data

object

原始响应

required

Example

{
  "task_id": "f186f65a-8657-4e83-b0e3-67facf1b2576",
  "data": {
    "requestId": "f186f65a-8657-4e83-b0e3-67facf1b2576"
  }
}

模型列表#

Request

Request samples

Responses

模型列表