Framepack API Create Task

Introduction

The Framepack Img2Video API allows you to generate videos from static images. This model is specially trained for long video generation

Model Information

Model: Qubico/framepack
Task Type: img2video
Description: Transforms static images into high-quality videos based on text and image prompts.

Pricing

$0.03 per second

Important Notes

Image Requirements

The input image can be provided as a URL or base64 encoded string.

For best results, provide clear images with good lighting and minimal background distractions.

Faces and human subjects generally produce the best results.

Video Generation Guidelines

Use detailed prompts to guide the video generation process.

Include specific motion descriptions in your prompt (e.g., "camera zooms in slowly," "gentle breeze moving hair").

The negative prompt can help avoid undesired artifacts or motions.

Duration

duration in seconds of the generated video

fps of the generated video sticks to 30

Request

Header Params

x-api-key

string

required

your api key

Body Params application/json

model

string

required

Model to use for generation

Example:

Qubico/framepack

task_type

string

required

Type of task to perform

Example:

img2video

input

object

required

prompt

string

required

Description of the video to generate

Example:

The camera zooms in, a video of a young woman with long, dark hair and bangs. She is wearing a light gray t-shirt and appears to be sitting at a table.

negative_prompt

string

optional

Description of elements to avoid in the generated video

Example:

chaotic, distortion, morphing

start_image

string

required

URL or base64 encoded image to transform into video, used as first frame

Example:

https://i.ibb.co/wbw9GLY/girl.webp

end_image

string

optional

URL or base64 encoded image to transform into video, used as end frame

Example:

https://i.ibb.co/wbw9GLY/girl.webp

duration

integer

optional

The duration (in seconds) of the generated video

>= 10<= 30

Default:

config

object

optional

webhook_config

object

optional

Example

{
  "model": "Qubico/framepack",
  "task_type": "img2video",
  "input": {
    "prompt": "The camera zooms in, a video of a young woman with long, dark hair and bangs. She is wearing a light gray t-shirt and appears to be sitting at a table.",
    "negative_prompt": "chaotic, distortion, morphing",
    "start_image": "https://i.ibb.co/wbw9GLY/girl.webp",
    "end_image": "https://i.ibb.co/wbw9GLY/girl.webp",
    "duration": 10
  }
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200OK

application/json

Successful operation

Body

task_id

string

optional

Unique identifier for the task

status

enum<string>

optional

Current status of the task

Allowed values:

pendingprocessingcompletedfailed

created_at

string <date-time>

optional

Timestamp when the task was created

Example

{
  "task_id": "string",
  "status": "pending",
  "created_at": "2019-08-24T14:15:22Z"
}

🟠400Bad Request

🟠401Unauthorized

🔴500Server Error

Create Task

Introduction#

Model Information#

Pricing#

Important Notes#

Image Requirements#

Video Generation Guidelines#

Duration#

Request

Request samples

Responses

Introduction

Model Information

Pricing

Important Notes

Image Requirements

Video Generation Guidelines

Duration