POST
/
video
/
scene_maker
Create scene transitions between images
curl --request POST \
  --url https://modelslab.com/api/v6/video/scene_maker \
  --header 'Content-Type: application/json' \
  --data '{
  "key": "<string>",
  "scenes": [
    {
      "img_url": "<string>",
      "start_frame_index": 123
    }
  ],
  "prompt": "<string>",
  "negative_prompt": "<string>",
  "height": 704,
  "width": 1280,
  "num_frames": 120,
  "seed": "<string>",
  "num_inference_steps": 50,
  "guidance_scale": 5,
  "stg_scale": 1,
  "stg_rescale": 0.7,
  "frame_rate": 25,
  "temp": false
}'
{
  "status": "success",
  "generationTime": 123,
  "id": 123,
  "output": [
    "<string>"
  ],
  "proxy_links": [
    "<string>"
  ],
  "future_links": [
    "<string>"
  ],
  "meta": {},
  "eta": 123,
  "message": "<string>",
  "tip": "<string>",
  "fetch_result": "<string>"
}

​
Scene Maker

Generate videos from a sequence of images.

​
Request

Make a POST request to below endpoint and pass the required parameters in the request body.
curl
--request POST 'https://modelslab.com/api/v6/video/scene_maker' \

​
Body

json
{
  "key":"",
  "prompt": "a women underwater swims out just to transform into old lady",
  "negative_prompt": "worst quality, inconsistent motion, blurry, jittery, distorted",
    "scenes": [
    {
      "img_url": "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/6P3f4I7fhwmtPfW127x7nqY5SYOkDu-metaMTExMS5qcGc=-.jpg",
      "start_frame_index": 0
    },
    {
      "img_url": "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/livewire-tmp/VHVDlpz1mSBcFQgiNrOhe5fG3BWrVn-metaMTExLmpwZw==-.jpg",
      "start_frame_index": 119
    }
  ],
  "num_frames": 120,
  "seed": 123456,
  "height": 704,
  "width": 1280,
  "num_inference_steps": 40,
  "guidance_scale": 5,
  "stg_scale": 1,
  "stg_rescale": 0.7,
  "frame_rate": 25,
  "base64": false
}

Body

application/json
​
key
string
required

Your API Key used for request authorization

​
scenes
object[]
required

Array of scene configurations

​
prompt
string
required

Text prompt for scene transitions

​
negative_prompt
string

Items to avoid during generation

​
height
integer
default:704

Output frame height

​
width
integer
default:1280

Output frame width

​
num_frames
integer
default:120

Total number of frames

​
seed
string

Seed for deterministic results

​
num_inference_steps
integer
default:50

Number of inference steps

​
guidance_scale
number
default:5

Guidance scale

​
stg_scale
number
default:1

Spatio temporal guidance scale

​
stg_rescale
number
default:0.7

Spatio temporal guidance factor

​
frame_rate
integer
default:25

Frame rate of output video

​
temp
boolean
default:false

Use temporary file storage

Response

Scene transition video response

​
status
enum<string>

Status of the video generation

Available options:
success,
processing,
error
​
generationTime
number

Time taken to generate the video in seconds

​
id
integer

Unique identifier for the video generation

​
output
string<uri>[]

Array of generated video URLs

​
proxy_links
string<uri>[]

Array of proxy video URLs

​
future_links
string<uri>[]

Array of future video URLs for queued requests

​
meta
object

Metadata about the video generation including all parameters used

​
eta
integer

Estimated time for completion in seconds (processing status)

​
message
string

Status message or additional information

​
tip
string

Additional information or tips for the user

​
fetch_result
string<uri>

URL to fetch the result when processing