curl --request POST \
--url https://api.apimart.ai/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
}'
import requests
url = "https://api.apimart.ai/v1/videos/generations"
payload = {
"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
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
const url = "https://api.apimart.ai/v1/videos/generations";
const payload = {
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
};
const headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://api.apimart.ai/v1/videos/generations"
payload := map[string]interface{}{
"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,
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer <token>")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;
public class Main {
public static void main(String[] args) throws Exception {
String url = "https://api.apimart.ai/v1/videos/generations";
String payload = """
{
"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
}
""";
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(url))
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payload))
.build();
HttpResponse<String> response = client.send(request,
HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}
<?php
$url = "https://api.apimart.ai/v1/videos/generations";
$payload = [
"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
];
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_HTTPHEADER, [
"Authorization: Bearer <token>",
"Content-Type: application/json"
]);
$response = curl_exec($ch);
curl_close($ch);
echo $response;
?>
require 'net/http'
require 'json'
require 'uri'
url = URI("https://api.apimart.ai/v1/videos/generations")
payload = {
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
}
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer <token>"
request["Content-Type"] = "application/json"
request.body = payload.to_json
response = http.request(request)
puts response.body
import Foundation
let url = URL(string: "https://api.apimart.ai/v1/videos/generations")!
let payload: [String: Any] = [
"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
]
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)
let task = URLSession.shared.dataTask(with: request) { data, response, error in
if let error = error {
print("Error: \(error)")
return
}
if let data = data, let responseString = String(data: data, encoding: .utf8) {
print(responseString)
}
}
task.resume()
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
var url = "https://api.apimart.ai/v1/videos/generations";
var payload = @"{
""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
}";
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");
var content = new StringContent(payload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
}
}
{
"code": 200,
"data": [
{
"status": "submitted",
"task_id": "task_01KPEY5H3NQ2W8D7T6VB3F9GR4"
}
]
}
{
"error": {
"code": 400,
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key",
"type": "authentication_error"
}
}
{
"error": {
"code": 402,
"message": "Insufficient account balance, please top up and try again",
"type": "payment_required"
}
}
{
"error": {
"code": 422,
"message": "Parameter conflict or invalid value (e.g. I2V and Omni fields passed simultaneously)",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 429,
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}
{
"error": {
"code": 500,
"message": "Internal server error, please retry later",
"type": "server_error"
}
}
SkyReels V4
Generación de Video SkyReels V4
- Dos niveles de modelo: Fast (optimizado para velocidad) y Std (optimizado para calidad)
- Tres modos enrutados automáticamente según los campos de la solicitud: Text-to-Video (T2V), Image-to-Video (I2V), Referencia multimodal (Omni)
- Resolución 480p / 720p / 1080p, duración de 3 a 15 segundos
- Funciones avanzadas: primer/último/fotograma clave, imágenes de referencia, videos de referencia, collage en cuadrícula, extensión de video, sincronización de audio
- Modo de procesamiento asíncrono, devuelve un ID de tarea para consultas posteriores
POST
/
v1
/
videos
/
generations
curl --request POST \
--url https://api.apimart.ai/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
}'
import requests
url = "https://api.apimart.ai/v1/videos/generations"
payload = {
"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
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
const url = "https://api.apimart.ai/v1/videos/generations";
const payload = {
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
};
const headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://api.apimart.ai/v1/videos/generations"
payload := map[string]interface{}{
"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,
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer <token>")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;
public class Main {
public static void main(String[] args) throws Exception {
String url = "https://api.apimart.ai/v1/videos/generations";
String payload = """
{
"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
}
""";
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(url))
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payload))
.build();
HttpResponse<String> response = client.send(request,
HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}
<?php
$url = "https://api.apimart.ai/v1/videos/generations";
$payload = [
"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
];
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_HTTPHEADER, [
"Authorization: Bearer <token>",
"Content-Type: application/json"
]);
$response = curl_exec($ch);
curl_close($ch);
echo $response;
?>
require 'net/http'
require 'json'
require 'uri'
url = URI("https://api.apimart.ai/v1/videos/generations")
payload = {
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
}
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer <token>"
request["Content-Type"] = "application/json"
request.body = payload.to_json
response = http.request(request)
puts response.body
import Foundation
let url = URL(string: "https://api.apimart.ai/v1/videos/generations")!
let payload: [String: Any] = [
"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
]
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)
let task = URLSession.shared.dataTask(with: request) { data, response, error in
if let error = error {
print("Error: \(error)")
return
}
if let data = data, let responseString = String(data: data, encoding: .utf8) {
print(responseString)
}
}
task.resume()
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
var url = "https://api.apimart.ai/v1/videos/generations";
var payload = @"{
""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
}";
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");
var content = new StringContent(payload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
}
}
{
"code": 200,
"data": [
{
"status": "submitted",
"task_id": "task_01KPEY5H3NQ2W8D7T6VB3F9GR4"
}
]
}
{
"error": {
"code": 400,
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key",
"type": "authentication_error"
}
}
{
"error": {
"code": 402,
"message": "Insufficient account balance, please top up and try again",
"type": "payment_required"
}
}
{
"error": {
"code": 422,
"message": "Parameter conflict or invalid value (e.g. I2V and Omni fields passed simultaneously)",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 429,
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}
{
"error": {
"code": 500,
"message": "Internal server error, please retry later",
"type": "server_error"
}
}
curl --request POST \
--url https://api.apimart.ai/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
}'
import requests
url = "https://api.apimart.ai/v1/videos/generations"
payload = {
"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
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
const url = "https://api.apimart.ai/v1/videos/generations";
const payload = {
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
};
const headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://api.apimart.ai/v1/videos/generations"
payload := map[string]interface{}{
"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,
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer <token>")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
import java.net.URI;
public class Main {
public static void main(String[] args) throws Exception {
String url = "https://api.apimart.ai/v1/videos/generations";
String payload = """
{
"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
}
""";
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create(url))
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.POST(HttpRequest.BodyPublishers.ofString(payload))
.build();
HttpResponse<String> response = client.send(request,
HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
}
}
<?php
$url = "https://api.apimart.ai/v1/videos/generations";
$payload = [
"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
];
$ch = curl_init($url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt($ch, CURLOPT_POST, true);
curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($payload));
curl_setopt($ch, CURLOPT_HTTPHEADER, [
"Authorization: Bearer <token>",
"Content-Type: application/json"
]);
$response = curl_exec($ch);
curl_close($ch);
echo $response;
?>
require 'net/http'
require 'json'
require 'uri'
url = URI("https://api.apimart.ai/v1/videos/generations")
payload = {
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
}
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = "Bearer <token>"
request["Content-Type"] = "application/json"
request.body = payload.to_json
response = http.request(request)
puts response.body
import Foundation
let url = URL(string: "https://api.apimart.ai/v1/videos/generations")!
let payload: [String: Any] = [
"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
]
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("Bearer <token>", forHTTPHeaderField: "Authorization")
request.setValue("application/json", forHTTPHeaderField: "Content-Type")
request.httpBody = try? JSONSerialization.data(withJSONObject: payload)
let task = URLSession.shared.dataTask(with: request) { data, response, error in
if let error = error {
print("Error: \(error)")
return
}
if let data = data, let responseString = String(data: data, encoding: .utf8) {
print(responseString)
}
}
task.resume()
using System;
using System.Net.Http;
using System.Text;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
var url = "https://api.apimart.ai/v1/videos/generations";
var payload = @"{
""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
}";
using var client = new HttpClient();
client.DefaultRequestHeaders.Add("Authorization", "Bearer <token>");
var content = new StringContent(payload, Encoding.UTF8, "application/json");
var response = await client.PostAsync(url, content);
var result = await response.Content.ReadAsStringAsync();
Console.WriteLine(result);
}
}
{
"code": 200,
"data": [
{
"status": "submitted",
"task_id": "task_01KPEY5H3NQ2W8D7T6VB3F9GR4"
}
]
}
{
"error": {
"code": 400,
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key",
"type": "authentication_error"
}
}
{
"error": {
"code": 402,
"message": "Insufficient account balance, please top up and try again",
"type": "payment_required"
}
}
{
"error": {
"code": 422,
"message": "Parameter conflict or invalid value (e.g. I2V and Omni fields passed simultaneously)",
"type": "invalid_request_error"
}
}
{
"error": {
"code": 429,
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}
{
"error": {
"code": 500,
"message": "Internal server error, please retry later",
"type": "server_error"
}
}
Autorización
string
requerido
Todos los endpoints de la API requieren autenticación mediante Bearer TokenObtenga su API Key:Visite la página de gestión de API Keys para obtener su API KeyAñádala al encabezado de la solicitud:
Authorization: Bearer YOUR_API_KEY
Modos de generación
SkyReels V4 se enruta automáticamente al modo correcto según los campos de la solicitud — no se necesita el campomode:
| Modo | Activador | Capacidad |
|---|---|---|
| T2V (Text-to-Video) | Solo prompt + campos generales | Generación basada únicamente en texto |
| I2V (Image-to-Video) | Cualquiera de first_frame_image / end_frame_image / mid_frame_images | Control de primer/último/fotograma clave |
| Omni (Referencia multimodal) | Cualquiera de ref_images / ref_videos | Referencia de sujeto, collage en cuadrícula, referencia de movimiento, extensión de video, sincronización de audio |
Exclusión mutua estricta: los campos I2V (
first_frame_image / end_frame_image / mid_frame_images) y los campos Omni (ref_images / ref_videos) no pueden usarse juntos; de lo contrario, se devuelve 422.Mecanismo
@tag: Al usar mid_frame_images / ref_images / ref_videos, cada elemento debe declarar un tag que comience con @ (por ejemplo, @image1, @Actor-1, @video1), y el tag debe aparecer en el prompt.Piense en el prompt como un “guion” y en el tag como un “puntero de personaje” hacia activos específicos (imágenes / videos). Por ejemplo, un prompt como "@Actor-1 walks into the scene of @video1" indica al sistema que inyecte el sujeto de la imagen de referencia ligado a @Actor-1 y la referencia de movimiento ligada a @video1 en el proceso de generación.Parámetros de la solicitud
Campos generales
string
requerido
Hay dos niveles de modelo disponibles:
| Modelo | Posicionamiento | Casos de uso |
|---|---|---|
skyreels-v4-fast | Prioriza velocidad | Vistas previas rápidas, generación por lotes, contenido diario |
skyreels-v4-std | Prioriza calidad (precio 25~30% superior al Fast) | Tomas clave, requisitos de alto detalle, entregas formales |
El campo
model debe proporcionarse explícitamente — no tiene valor por defecto.El precio está fuertemente ligado a la resolución y al uso de
ref_videos: 1080p es significativamente más caro que 480p / 720p; los niveles con ref_videos (entrada de video) cuestan ~1.5 ~ 2× en comparación con los que no lo usan. Aún no se admite la salida simultánea de audio y video.boolean
predeterminado:"false"
Indica si se debe moderar el contenido antes de enviar la tarea de vídeo.
true: revisar los prompts y las imágenes de entrada conomni-moderation-latestfalseu omitido: no enviar una solicitud de moderación, sin coste ni latencia de moderación adicionales (predeterminado)
string
requerido
Prompt de texto, máximo 1280 tokensDescriba escenas, sujetos, acciones y estilos en detalle para obtener mejores resultados.Al usar
ref_images / ref_videos / mid_frame_images, el prompt debe contener el @tag correspondiente (por ejemplo, @Actor-1, @video1, @image1).Ejemplo: "@Actor-1 walks through a neon-lit street at night."integer
predeterminado:"5"
Duración del video de salida (segundos)
- Rango:
[3, 15] - Por defecto:
5
Cuando se proporciona
ref_videos.type=reference, duration se sobrescribe con la longitud del video de referencia (máx. 10 segundos).string
predeterminado:"1080p"
Resolución del videoOpciones:
480p720p1080p(por defecto)
string
predeterminado:"16:9"
Proporción de aspectoOpciones:
16:9(por defecto)4:31:19:163:4
aspect_ratio se ignora en modo I2V (la proporción de salida la determina la imagen de entrada); también se ignora cuando Omni se combina con ref_videos.boolean
predeterminado:"true"
Si se debe optimizar el prompt automáticamenteCuando está activado, el sistema optimiza automáticamente su prompt para obtener mejores resultados.
Campos específicos de I2V
string
URL de la imagen del primer fotograma (jpg / jpeg / png / gif / bmp)Cuando se proporciona, esta imagen se utiliza como fotograma inicial del video.
string
URL de la imagen del último fotograma (jpg / jpeg / png / gif / bmp)Cuando se proporciona, esta imagen se utiliza como fotograma final del video. Puede combinarse con
first_frame_image para el control de primer y último fotograma.object[]
Lista de fotogramas clave intermedios, hasta 6. Cada elemento tiene la siguiente estructura:
Mostrar elemento mid_frame_images
Mostrar elemento mid_frame_images
string
requerido
Debe comenzar con
@ y aparecer en el prompt, por ejemplo, @image1string
requerido
URL de la imagen (jpg / jpeg / png / gif / bmp)
integer
predeterminado:"-1"
Marca temporal de aparición (segundos). Por defecto
-1 (sin especificar); cuando se especifica, debe cumplir 0 < time_stamp < duration.Campos específicos de Omni
object[]
Lista de imágenes de referencia (todos los elementos deben compartir el mismo
type). Cada elemento tiene la siguiente estructura:Mostrar elemento ref_images
Mostrar elemento ref_images
string
requerido
Debe comenzar con
@ y aparecer en el prompt, por ejemplo, @Actor-1string
requerido
Tipo de referencia:
image- Imagen de referencia regular (longitud de lista 13; cada5)image_urlscon longitud 1grid- Collage en cuadrícula, es decir, una sola imagen compuesta por múltiples mosaicos (por ejemplo, 2×2, 3×3); la longitud de la lista debe ser 1,image_urlsdebe ser 1 imagen
string[]
requerido
Array de URLs de imágenes
string
URL de audio de voz (solo soportado cuando
type=image, duración del audio ≤ 15 segundos)object[]
Lista de videos de referencia, hasta 1. Cada elemento tiene la siguiente estructura:
Mostrar elemento ref_videos
Mostrar elemento ref_videos
string
requerido
Debe comenzar con
@ y aparecer en el prompt, por ejemplo, @video1string
requerido
Tipo de referencia:
reference- Referencia de movimiento / sujeto, sobrescribeduration(sigue la longitud del video de referencia, máx. 10 segundos), incluye por defecto el audio del video de entrada; puede combinarse conref_images.type=imageextend- Extensión de video, facturada según ladurationsolicitada; no puede combinarse conref_images
string
requerido
URL del video (MP4 / MOV, duración ≤ 15 segundos)
Escenarios soportados
Los siguientes escenarios son soportados tanto porskyreels-v4-fast como por skyreels-v4-std:
| Escenario | Modo | Campos requeridos | Caso de uso típico |
|---|---|---|---|
| Text-to-Video | T2V | prompt | Generación basada en texto puro, tomas conceptuales rápidas |
| Image-to-Video - Primer fotograma | I2V | first_frame_image | Imagen estática a video con un fotograma inicial especificado |
| Image-to-Video - Último fotograma | I2V | end_frame_image | Especifica el fotograma de cierre |
| Image-to-Video - Fotogramas clave | I2V | mid_frame_images (1 ~ 6) | Primer + último + fotogramas clave intermedios para un ritmo preciso |
| Omni Sujeto único/múltiple | Omni | ref_images (type=image) | Consistencia de personaje, encuadre multi-sujeto |
| Omni Collage en cuadrícula | Omni | ref_images (type=grid, 1 imagen) | Videos paso a paso (tutoriales, recetas, demos) |
| Omni Referencia de movimiento | Omni | ref_videos (type=reference) | Replicar el movimiento, sujeto o estilo de un video de referencia |
| Omni Extensión de video | Omni | ref_videos (type=extend) | Continuar un video existente con contenido nuevo |
| Omni Sincronización de audio | Omni | ref_images (type=image) + audio_url | Narración con humano digital, lip-sync impulsado por audio |
Restricciones de parámetros
Violar cualquiera de las siguientes hará que la solicitud sea rechazada con una respuesta 422, sin facturación:| Parámetro | Restricción |
|---|---|
prompt | Máximo 1280 tokens |
duration | [3, 15] segundos; sobrescrito por la longitud del video de referencia (máx. 10s) cuando ref_videos.type=reference |
resolution | Solo 480p / 720p / 1080p |
aspect_ratio | 16:9 / 4:3 / 1:1 / 9:16 / 3:4; ignorado en I2V; ignorado cuando Omni incluye ref_videos |
mid_frame_images | Hasta 6; time_stamp debe ser -1 o estar dentro de (0, duration) |
ref_images general | Todos los elementos deben compartir el mismo type; no puede coexistir con campos I2V |
ref_images.type=grid | Longitud de lista debe ser 1; image_urls debe ser 1 imagen |
ref_images.type=image | Longitud de lista 1 ~ 3; cada image_urls con longitud 1 ~ 5 |
ref_images.audio_url | Solo soportado cuando type=image, audio ≤ 15 segundos |
ref_videos | Hasta 1; video_url MP4 / MOV, ≤ 15 segundos |
ref_videos.type=reference | Sobrescribe la duration solicitada (máx. 10s), puede combinarse con ref_images.type=image, incluye por defecto el audio del video de entrada |
ref_videos.type=extend | Facturado por la duration solicitada; no puede combinarse con ref_images |
Campo tag | Debe comenzar con @ y aparecer en el prompt |
| Exclusión I2V / Omni | Los campos I2V y Omni no pueden usarse juntos |
Respuesta
integer
Código de estado de la respuesta, 200 en caso de éxito
array
Ejemplos de solicitud
Caso 1: Texto a video (mínimo)
{
"model": "skyreels-v4-fast",
"prompt": "A serene forest at sunset with golden light filtering through the trees."
}
Caso 2: Texto a video (parámetros completos)
{
"model": "skyreels-v4-std",
"prompt": "A serene forest at sunset.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"prompt_optimizer": true
}
Caso 3: Imagen a video - Primer fotograma
{
"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
}
Caso 4: Imagen a video - Primer/Último fotograma + fotogramas clave intermedios
{
"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 }
]
}
Caso 5: Omni - Referencia de sujeto único
{
"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"] }
]
}
Caso 6: Omni - Multi-sujeto + referencia de movimiento por video
{
"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" }
]
}
Este caso usa
ref_videos.type=reference, por lo que la duration solicitada será sobrescrita por la longitud real del video de referencia (máx. 10 segundos). Aunque aquí se pase "duration": 5, la duración final del video sigue la del video de referencia.Caso 7: Omni - Collage en cuadrícula
{
"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"] }
]
}
Caso 8: Omni - Extensión de video (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" }
]
}
Caso 9: Omni - Sincronización de audio (impulsado por voz)
{
"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"
}
]
}
Consultar resultados de la tareaLa generación de video es una tarea asíncrona que devuelve un
task_id al enviarse. Use el endpoint Obtener estado de la tarea para consultar el progreso y los resultados de la generación.⌘I