Create Video Generation Task

This API is designed to integrate the generation function interfaces provided by various deployers, extract commonly used parameter fields and response fields, standardize field naming and parameter/response data formats, and improve usage efficiency.
This API supports parameter passing in both form-data and JSON formats.
This API only focuses on obtaining task_id. If you need to query other information, you can obtain it through the data field.

Pricing: Charged according to the corresponding video model

Model List

Model Name	Description	302ai Original Documentation Link
stable_diffusion	Generates a short video based on an initial image using Stable Video Diffusion	https://302ai.apifox.cn/api-163311828
luma_video	Text/image-to-video from Luma AI. Generates a 5s video from text or image. Supports specifying first and last frames for connection.	https://302ai.apifox.cn/api-187178782
runway_gen3_t2v	Text-to-video from Runway Gen-3, generates a 10s video from text.	https://302ai.apifox.cn/api-189493613
runway_gen3_i2v	Image-to-video from Runway Gen-3, generates a 10s video from an image.	https://302ai.apifox.cn/api-199355546
runway_gen3_v2v	Video-to-video from Runway Gen-3, transforms the original video into different styles based on video and prompts	https://302ai.apifox.cn/api-223390968
runway_gen3_i2v_turbo	Fast image-to-video from Runway Gen-3-turbo, generates a 5 or 10s video from an image. API format updated on 2024/10/10, supports first and last frame generation	https://302ai.apifox.cn/api-205655192
runway_gen3_v2v_turbo	Fast video-to-video from Runway Gen-3-turbo	https://302ai.apifox.cn/api-223738811
runway_gen3_v2v_turbo	Fast video-to-video from Runway Gen-3-turbo	https://302ai.apifox.cn/api-223738811
kling_10_t2v	Text-to-video from Kling, using the kling-1.0 model	https://302ai.apifox.cn/api-198887177
kling_15_t2v_hq	Text-to-video from Kling, using the kling-1.5 model	https://302ai.apifox.cn/api-198886960
kling_16_t2v	Text-to-video from Kling, using the kling-1.6 model	https://302ai.apifox.cn/api-246734393
kling_16_t2v_hq	Text-to-video from Kling, using the kling-1.6 high-definition model	https://302ai.apifox.cn/api-246743000
kling_10_i2v	Image-to-video from Kling, using the kling-1.0 model	https://302ai.apifox.cn/api-199351654
kling_15_i2v	Image-to-video from Kling, using the kling-1.5 model	https://302ai.apifox.cn/api-237203461
kling_15_i2v_hq	Image-to-video from Kling, using the kling-1.5 high-definition model	https://302ai.apifox.cn/api-199350561
kling_16_i2v	Image-to-video from Kling, using the kling-1.6 model	https://302ai.apifox.cn/api-246757102
kling_16_i2v_hq	Image-to-video from Kling, using the kling-1.6 high-definition model	https://302ai.apifox.cn/api-246758657
cog_t2v	Text-to-video model from Zhipu	https://302ai.apifox.cn/api-201750151
cog_i2v	Image-to-video model from Zhipu	https://302ai.apifox.cn/api-201750620
minimaxi_T2V-01	Text-to-video model from Minimax	https://302ai.apifox.cn/api-211530859
minimaxi_T2V-01-Director	Text-to-video model from Minimax	https://302ai.apifox.cn/api-211530859
minimaxi_I2V-01	Image-to-video model from Minimax	https://302ai.apifox.cn/api-222410342
minimaxi_I2V-01-live	Image-to-video model from Minimax	https://302ai.apifox.cn/api-222410342
minimaxi_I2V-01-Director	Image-to-video model from Minimax	https://302ai.apifox.cn/api-222410342
minimaxi_S2V-01	Subject-to-video model from Minimax	https://302ai.apifox.cn/api-256524539
minimaxi_hailuo_02_t2v	Text-to-video function of MiniMax-hailuo-02 model from Minimax	https://302ai.apifox.cn/api-310678678
minimaxi_hailuo_02_i2v	Image-to-video function of MiniMax-hailuo-02 model from Minimax	https://302ai.apifox.cn/api-310678678
pika_1.0	Image/text-to-video model from pika, using version 1.0	https://302ai.apifox.cn/api-252576908
pika_1.5	Image/text-to-video model from pika, using version 1.5	https://302ai.apifox.cn/api-252576908
pika_2.0	Image/text-to-video model from pika, using version 2.0	https://302ai.apifox.cn/api-252576908
pika_2.0-contextualize	Reference subject-to-video model from pika	https://302ai.apifox.cn/api-252638488
pixverse_v2	Image-to-video function from pixverse, using version V2	https://302ai.apifox.cn/api-236242446
pixverse_v3	Image-to-video function from pixverse, using version V3	https://302ai.apifox.cn/api-236242446
pixverse_v3.5	Image-to-video function from pixverse, using version V3.5	https://302ai.apifox.cn/api-236242446
pixverse_v4	Image-to-video function from pixverse, using version V4	https://302ai.apifox.cn/api-236242446
genmo_t2v	Genmo has open-sourced its latest video generation model Mochi1, setting a new benchmark in the field. Mochi1 adopts the innovative Asymmetric Diffusion Transformer (AsymmDiT) architecture	https://302ai.apifox.cn/api-226102617
haiper_20_t2v	An emerging video generation company from London, version 2.0 text-to-video function	https://302ai.apifox.cn/api-231796551
haiper_20_i2v	An emerging video generation company from London, version 2.0 image-to-video function	https://302ai.apifox.cn/api-231796575
haiper_25_t2v	An emerging video generation company from London, version 2.5 text-to-video function	https://302ai.apifox.cn/api-256276024
haiper_20_i2v	An emerging video generation company from London, version 2.5 image-to-video function	https://302ai.apifox.cn/api-256276025
ltx_t2v	Open-source text-to-video model, features extremely fast generation. Note: The more detailed the prompt, the better the result. Otherwise, the effect is poor.	https://302ai.apifox.cn/api-236951967
ltx_i2v	Open-source image-to-video model, features extremely fast generation. Note: The image should be in 3:2 ratio, otherwise it will be stretched.	https://302ai.apifox.cn/api-236951967
ltx_095_t2v	Open-source text-to-video model, features extremely fast generation. Note: The more detailed the prompt, the better the result. Otherwise, the effect is poor.	https://302ai.apifox.cn/api-268402418
ltx_095_i2v	Open-source image-to-video model, features extremely fast generation. Note: The image should be in 3:2 ratio, otherwise it will be stretched.	https://302ai.apifox.cn/api-268402419
wanx2.1-t2v-turbo	Official Tongyi Wanxiang model. Feature: Faster generation speed, balanced performance	https://302ai.apifox.cn/api

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

application/json

Body

Example

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

Model List#

Request

Request Code Samples

Responses

Model List