Stability.Ai
  1. generation
Stability.Ai
  • Getting Started
  • v1
    • user
      • account
      • balance
    • engines
      • list
    • generation
      • text-to-image
      • image-to-image
      • image-to-image/upscale
      • image-to-image/masking
  • v2alpha
    • generation
      • image-to-video
        POST
      • image-to-video/result
        GET
      • stable-image/upscale
        POST
      • stable-image/upscale/result
        GET
      • stable-image/inpaint
        POST
  1. generation

image-to-video

https://api.stability.ai
https://api.stability.ai
https://api.stability.ai
https://api.stability.ai
POST
/v2alpha/generation/image-to-video
v2alpha/generation
Generate a short video based on an initial image with Stable Video Diffusion,
a latent video diffusion model.

How to generate a video:#

Video generations are asynchronous, so after starting a generation use the id returned in the response to poll /v2alpha/generation/image-to-video/result/{id} for results.
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST 'https://api.stability.ai/v2alpha/generation/image-to-video' \
--header 'authorization;' \
--form 'image=@"./some/image.png"'
Response Response Example
200 - Example 1
{
    "id": "a6dc6c6e20acda010fe14d71f180658f2896ed9b4ec25aa99a6ff06c796987c4"
}

Request

Header Params
authorization
string 
required
content-type
string 
required
Body Params multipart/form-data
image
file 
required
The source image used in the video generation process.
Please ensure that the source image is in the correct format and dimensions.
Supported Formats:
jpeg
png
Supported Dimensions:
1024x576
576x1024
768x768
Example:
./some/image.png
seed
number 
optional
A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass 0 to use a random seed.)
cfg_scale
number 
optional
How strongly the video sticks to the original image. Use lower values to allow the model more freedom to make changes and higher values to correct motion distortions.
Example:
1.8
motion_bucket_id
number 
optional
Lower values generally result in less motion in the output video, while higher values generally result in more motion. This parameter corresponds to the motion_bucket_id parameter from the paper.
Example:
127

Responses

🟢200Video generation started. Poll for results using the `id` in the response [here](#tag/v2alphageneration/paths/~1v2alpha~1generation~1image-to-video~1result~1%7Bid%7D/get).
application/json
Body
id
string 
required
The id of a generation, typically used for async generations, that can be used to check the status of the generation or retrieve the result.
>= 64 characters<= 64 characters
Example:
a6dc6c6e20acda010fe14d71f180658f2896ed9b4ec25aa99a6ff06c796987c4
🟠400Something about your request is invalid, see the `errors` field for details.
🔴500An internal error occurred. If the problem persists [contact support](https://platform.stability.ai/support).
Previous
image-to-image/masking
Next
image-to-video/result
Built with