Skip to main content
POST
/
kyyReactApiServer
/
v1
/
videos
/
videos
curl --request POST \
  --url https://zcbservice.aizfw.cn/kyyReactApiServer/v1/videos/videos \
  --header 'Authorization: Bearer {{key}}' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "videos",
    "prompt": "A cute kitten playing in the grass, bright daylight, cinematic camera",
    "duration": 5,
    "ratio": "16:9",
    "resolution": "720p"
  }'
{
  "code": "0",
  "msg": null,
  "data": {
    "projectId": "proj_1234567890"
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.globalaiopc.com/llms.txt

Use this file to discover all available pages before exploring further.

Videos Create Video Task

Create video generation tasks using the Videos model family. This API supports standard and fast models, text-to-video, first/last frame control, reference images, reference videos, and mixed image-video guidance.

Authentication

All requests require a Bearer token in the request header:
Authorization: Bearer {{key}}

Model Overview

Supported models:
  • videos - Standard model, billed per request
  • videos_fast - Fast model, billed per request

Request Parameters

model
string
required
Model name.Available values:
  • videos - Standard model
  • videos_fast - Fast model
prompt
string
required
Video generation prompt. Maximum length is 1500 characters.Avoid prohibited, infringing, political, or explicit content.Example: "A cute kitten playing in the grass"
duration
integer
required
Video duration in seconds. Supported range: 4-15.
ratio
string
Output aspect ratio. Defaults to 16:9.Supported values:
  • 16:9 - Landscape
  • 9:16 - Portrait
resolution
string
Output resolution. Defaults to 720p.Currently supported:
  • 720p

First/Last Frame Mode

image
string
First frame image URL.
  • Only used for first/last frame scenarios
  • Must be used together with lastFrameImage
Cannot be used together with referenceImages or referenceVideos
lastFrameImage
string
Last frame image URL.
  • Must be used together with image
Cannot be used together with referenceImages or referenceVideos

Reference Material Mode

referenceImages
array
Reference image URL list.Rules:
  • Up to 4 images
  • Each image must not exceed 20MB
  • Can be combined with referenceVideos for mixed guidance
Cannot be used together with image or lastFrameImage
referenceVideos
array
Reference video URL list.Rules:
  • Up to 3 videos
  • Total duration must not exceed 15 seconds
  • Total size must not exceed 200MB
  • Each video must have a resolution between 720px and 2160px
Cannot be used together with image or lastFrameImage

Response Parameters

code
string
Status code. 0 indicates success.
msg
string
Response message. Usually contains the error reason on failure.
data.projectId
string
Task ID.Used for subsequent status and result queries.

Parameter Selection Rules

Mutually Exclusive Rules:
  • First/last frame mode: image and lastFrameImage must be used together
  • Reference material mode: referenceImages and referenceVideos can be used individually or together
  • Mode exclusivity: First/last frame mode cannot be combined with reference material mode

Use Cases

Text to Video

Use only prompt, model, duration, and other base parameters

First/Last Frame

Use image and lastFrameImage for precise start and end frame control

Mixed References

Combine referenceImages and referenceVideos for stronger visual constraints

Model Comparison

ModelBillingDuration RangeBest For
videosPer request4-15 secondsStandard quality workflows
videos_fastPer request4-15 secondsSpeed-sensitive generation scenarios
Best Practices:
  1. Video generation is asynchronous, so save the returned task ID for later queries.
  2. Include scene, subject, motion, camera, and style details in the prompt.
  3. In first/last frame mode, make sure the two images are visually continuous.
  4. When using video references, prefer short, clear, and subject-focused source materials.
  5. Use videos for more stable results and videos_fast when latency matters more.
Prompt Suggestions:
  • Describe the subject, action, and camera movement
  • Add style keywords such as “cinematic”, “realistic”, or “dreamlike”
  • If you need camera motion or scene transitions, describe them explicitly
curl --request POST \
  --url https://zcbservice.aizfw.cn/kyyReactApiServer/v1/videos/videos \
  --header 'Authorization: Bearer {{key}}' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "videos",
    "prompt": "A cute kitten playing in the grass, bright daylight, cinematic camera",
    "duration": 5,
    "ratio": "16:9",
    "resolution": "720p"
  }'
{
  "code": "0",
  "msg": null,
  "data": {
    "projectId": "proj_1234567890"
  }
}