SkyReels V4 Video Generation

curl --request POST \
  --url https://gccai.heqingsong.uk/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "skyreels-v4-fast",
    "prompt": "A serene forest at sunset with golden light filtering through the trees.",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "prompt_optimizer": true
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01KPEY5H3NQ2W8D7T6VB3F9GR4"
    }
  ]
}

POST

videos

generations

curl --request POST \
  --url https://gccai.heqingsong.uk/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "skyreels-v4-fast",
    "prompt": "A serene forest at sunset with golden light filtering through the trees.",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "prompt_optimizer": true
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01KPEY5H3NQ2W8D7T6VB3F9GR4"
    }
  ]
}

curl --request POST \
  --url https://gccai.heqingsong.uk/v1/videos/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "skyreels-v4-fast",
    "prompt": "A serene forest at sunset with golden light filtering through the trees.",
    "duration": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "prompt_optimizer": true
  }'

{
  "code": 200,
  "data": [
    {
      "status": "submitted",
      "task_id": "task_01KPEY5H3NQ2W8D7T6VB3F9GR4"
    }
  ]
}

Authorization

string

required

All API endpoints require Bearer Token authenticationGet your API Key:Visit the API Key Management Page to get your API KeyAdd to the request header:

Authorization: Bearer YOUR_API_KEY

Generation Modes

SkyReels V4 auto-routes to the correct mode based on request fields — no mode field needed:

Mode	Trigger	Capability
T2V (Text-to-Video)	Only `prompt` + general fields	Pure text-driven generation
I2V (Image-to-Video)	Any of `first_frame_image` / `end_frame_image` / `mid_frame_images`	First/end/key frame control
Omni (Multimodal Reference)	Any of `ref_images` / `ref_videos`	Subject reference, grid collage, motion reference, video extension, audio sync

Strict mutual exclusion: I2V fields (first_frame_image / end_frame_image / mid_frame_images) and Omni fields (ref_images / ref_videos) cannot be used together, otherwise returns 422.

@tag mechanism: When using mid_frame_images / ref_images / ref_videos, each element must declare a tag starting with @ (e.g., @image1, @Actor-1, @video1), and the tag must appear in the prompt.Think of prompt as the “script” and tag as a “character pointer” to specific assets (images / videos). For example, a prompt like "@Actor-1 walks into the scene of @video1" instructs the system to inject the reference image subject tied to @Actor-1 and the motion reference tied to @video1 into the generation process.

Request Parameters

General Fields

model

string

required

Two model tiers are available:

Model	Positioning	Use Cases
`skyreels-v4-fast`	Speed-first	Quick previews, batch generation, daily content
`skyreels-v4-std`	Quality-first (25~30% higher price than Fast)	Key shots, high-detail requirements, formal delivery

The model field must be explicitly provided — no default value.

Pricing is strongly tied to resolution and whether ref_videos is used: 1080p is significantly more expensive than 480p / 720p; tiers with ref_videos (video input) cost ~1.5 ~ 2× compared to those without. Simultaneous audio and video output is not yet supported.

prompt

string

required

Text prompt, max 1280 tokensDescribe scenes, subjects, actions, styles in detail for better generation results.When using ref_images / ref_videos / mid_frame_images, the prompt must contain the corresponding @tag (e.g., @Actor-1, @video1, @image1).Example: "@Actor-1 walks through a neon-lit street at night."

duration

integer

default:"5"

Output video duration (seconds)

Range: [3, 15]
Default: 5

When ref_videos.type=reference is provided, duration is overridden by the reference video length (max 10 seconds).

resolution

string

default:"1080p"

Video resolutionOptions:

480p
720p
1080p (default)

aspect_ratio

string

default:"16:9"

Aspect ratioOptions:

16:9 (default)
4:3
1:1
9:16
3:4

aspect_ratio is ignored in I2V mode (output ratio is determined by the input image); also ignored when Omni is combined with ref_videos.

prompt_optimizer

boolean

default:"true"

Whether to auto-optimize the promptWhen enabled, the system automatically optimizes your prompt for better generation results.

I2V-Specific Fields

first_frame_image

string

First frame image URL (jpg / jpeg / png / gif / bmp)When provided, this image is used as the starting frame of the video.

end_frame_image

string

End frame image URL (jpg / jpeg / png / gif / bmp)When provided, this image is used as the ending frame of the video. Can be combined with first_frame_image for first-and-last-frame control.

mid_frame_images

object[]

Mid keyframe list, up to 6. Each element has the following structure:

Show mid_frame_images element

tag

string

required

Must start with @ and appear in the prompt, e.g., @image1

image_url

string

required

Image URL (jpg / jpeg / png / gif / bmp)

time_stamp

integer

default:"-1"

Timestamp of appearance (seconds). Default -1 (unspecified); when specified, must satisfy 0 < time_stamp < duration.

Omni-Specific Fields

ref_images

object[]

Reference image list (all elements must share the same type). Each element has the following structure:

Show ref_images element

tag

string

required

Must start with @ and appear in the prompt, e.g., @Actor-1

type

string

required

Reference type:

image - Regular reference image (list length 1~~3; each image_urls length 1~~5)
grid - Grid collage, i.e., a single image composed of multiple tiles (e.g., 2×2, 3×3); list length must = 1, image_urls must be 1 image

image_urls

string[]

required

Array of image URLs

audio_url

string

Voice audio URL (only supported when type=image, audio duration ≤ 15 seconds)

ref_videos

object[]

Reference video list, up to 1. Each element has the following structure:

Show ref_videos element

tag

string

required

Must start with @ and appear in the prompt, e.g., @video1

type

string

required

Reference type:

reference - Motion / subject reference, overrides duration (follows the reference video length, max 10 seconds), carries input video audio by default; can be combined with ref_images.type=image
extend - Video extension, billed by the requested duration; cannot be combined with ref_images

video_url

string

required

Video URL (MP4 / MOV, duration ≤ 15 seconds)

Supported Scenarios

The following scenarios are supported by both skyreels-v4-fast and skyreels-v4-std:

Scenario	Mode	Required Fields	Typical Use Case
Text-to-Video	T2V	`prompt`	Pure text-driven, rapid concept shots
Image-to-Video - First Frame	I2V	`first_frame_image`	Still-to-video with a specified starting frame
Image-to-Video - End Frame	I2V	`end_frame_image`	Specifies the closing frame
Image-to-Video - Keyframes	I2V	`mid_frame_images` (1 ~ 6)	First + end + mid keyframes for precise pacing
Omni Single/Multi-Subject	Omni	`ref_images` (`type=image`)	Character consistency, multi-subject framing
Omni Grid Collage	Omni	`ref_images` (`type=grid`, 1 image)	Step-by-step process videos (tutorials, recipes, demos)
Omni Motion Reference	Omni	`ref_videos` (`type=reference`)	Replicate the motion, subject, or style of a reference video
Omni Video Extension	Omni	`ref_videos` (`type=extend`)	Continue an existing video with new content
Omni Audio Sync	Omni	`ref_images` (`type=image`) + `audio_url`	Digital human narration, audio-driven lip-sync

Parameter Constraints

Violating any of the following will cause the request to be rejected with a 422 response, no billing occurs:

Parameter	Constraint
`prompt`	Max 1280 tokens
`duration`	`[3, 15]` seconds; overridden by reference video length (max 10s) when `ref_videos.type=reference`
`resolution`	Only `480p` / `720p` / `1080p`
`aspect_ratio`	`16:9` / `4:3` / `1:1` / `9:16` / `3:4`; ignored in I2V; ignored when Omni carries `ref_videos`
`mid_frame_images`	Up to 6; `time_stamp` must be `-1` or within `(0, duration)`
`ref_images` overall	All elements must share the same `type`; cannot coexist with I2V fields
`ref_images.type=grid`	List length must = 1; `image_urls` must be 1 image
`ref_images.type=image`	List length 1 ~ 3; each `image_urls` length 1 ~ 5
`ref_images.audio_url`	Only supported when `type=image`, audio ≤ 15 seconds
`ref_videos`	Up to 1; `video_url` MP4 / MOV, ≤ 15 seconds
`ref_videos.type=reference`	Overrides requested `duration` (max 10s), can combine with `ref_images.type=image`, carries input video audio by default
`ref_videos.type=extend`	Billed by requested `duration`; cannot combine with `ref_images`
`tag` field	Must start with `@` and appear in the `prompt`
I2V / Omni exclusion	I2V fields and Omni fields cannot be used together

Response

code

integer

Response status code, 200 on success

data

array

Response data array

Show Array Elements

status

string

Task status, submitted when initially submitted

task_id

string

Unique task identifier for querying task status and results

Request Examples

Case 1: Text-to-Video (Minimal)

{
  "model": "skyreels-v4-fast",
  "prompt": "A serene forest at sunset with golden light filtering through the trees."
}

Case 2: Text-to-Video (Full Parameters)

{
  "model": "skyreels-v4-std",
  "prompt": "A serene forest at sunset.",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "prompt_optimizer": true
}

Case 3: Image-to-Video - First Frame

{
  "model": "skyreels-v4-fast",
  "prompt": "Slowly pull the camera back to reveal the entire scene.",
  "first_frame_image": "https://example.com/start.png",
  "duration": 5
}

Case 4: Image-to-Video - First/End Frame + Mid Keyframes

{
  "model": "skyreels-v4-std",
  "prompt": "The King summons a flying dragon. @image1 The dragon lowers. The King mounts and flies away.",
  "duration": 8,
  "resolution": "1080p",
  "first_frame_image": "https://example.com/k2v_0.png",
  "end_frame_image":   "https://example.com/k2v_2.png",
  "mid_frame_images": [
    { "tag": "@image1", "image_url": "https://example.com/k2v_1.png", "time_stamp": 3 }
  ]
}

Case 5: Omni - Single Subject Reference

{
  "model": "skyreels-v4-fast",
  "prompt": "@Actor-1 walks through a neon-lit street at night.",
  "ref_images": [
    { "tag": "@Actor-1", "type": "image", "image_urls": ["https://example.com/actor.jpg"] }
  ]
}

Case 6: Omni - Multi-Subject + Video Motion Reference

{
  "model": "skyreels-v4-fast",
  "prompt": "The man from @image_1 imitates the move on the left in @video_1. The woman from @image_2 imitates the right side.",
  "duration": 5,
  "ref_images": [
    { "tag": "@image_1", "type": "image", "image_urls": ["https://example.com/a.png"] },
    { "tag": "@image_2", "type": "image", "image_urls": ["https://example.com/b.png"] }
  ],
  "ref_videos": [
    { "tag": "@video_1", "type": "reference", "video_url": "https://example.com/motion.mp4" }
  ]
}

This case uses ref_videos.type=reference, so the requested duration will be overridden by the actual reference video length (max 10 seconds). Even though "duration": 5 is passed here, the final video length follows the reference video.

Case 7: Omni - Grid Collage

{
  "model": "skyreels-v4-fast",
  "prompt": "Create a video showing how to make tomato and egg noodles based on @image1.",
  "ref_images": [
    { "tag": "@image1", "type": "grid", "image_urls": ["https://example.com/recipe_grid.png"] }
  ]
}

Case 8: Omni - Video Extension (extend)

{
  "model": "skyreels-v4-fast",
  "prompt": "Video extended @video1, someone walks over and sits on the sofa.",
  "duration": 8,
  "ref_videos": [
    { "tag": "@video1", "type": "extend", "video_url": "https://example.com/source.mp4" }
  ]
}

Case 9: Omni - Audio Sync (Voice-Driven)

{
  "model": "skyreels-v4-std",
  "prompt": "@Actor-1 speaks with a calm tone.",
  "ref_images": [
    {
      "tag": "@Actor-1",
      "type": "image",
      "image_urls": ["https://example.com/actor.jpg"],
      "audio_url":  "https://example.com/voice.mp3"
    }
  ]
}

Query Task ResultsVideo generation is an async task that returns a task_id upon submission. Use the Get Task Status endpoint to query generation progress and results.

MiniMax-Hailuo-2.3 Video Generation HappyHorse 1.0 Video Generation

Documentation Index

​Authorization

​Generation Modes

​Request Parameters

​General Fields

​I2V-Specific Fields

​Omni-Specific Fields

​Supported Scenarios

​Parameter Constraints

​Response

​Request Examples

​Case 1: Text-to-Video (Minimal)

​Case 2: Text-to-Video (Full Parameters)

​Case 3: Image-to-Video - First Frame

​Case 4: Image-to-Video - First/End Frame + Mid Keyframes

​Case 5: Omni - Single Subject Reference

​Case 6: Omni - Multi-Subject + Video Motion Reference

​Case 7: Omni - Grid Collage

​Case 8: Omni - Video Extension (extend)

​Case 9: Omni - Audio Sync (Voice-Driven)

Authorization

Generation Modes

Request Parameters

General Fields

I2V-Specific Fields

Omni-Specific Fields

Supported Scenarios

Parameter Constraints

Response

Request Examples

Case 1: Text-to-Video (Minimal)

Case 2: Text-to-Video (Full Parameters)

Case 3: Image-to-Video - First Frame

Case 4: Image-to-Video - First/End Frame + Mid Keyframes

Case 5: Omni - Single Subject Reference

Case 6: Omni - Multi-Subject + Video Motion Reference

Case 7: Omni - Grid Collage

Case 8: Omni - Video Extension (extend)

Case 9: Omni - Audio Sync (Voice-Driven)