Create Asset Generator task

This endpoint generates a lipsync v2 video.

POST /api/asset_generator

cURL

cURL

curl --request POST \
  --url https://api.creatify.ai/api/asset_generator/ \
  --header 'Content-Type: application/json' \
  --header 'X-API-ID: <api-key>' \
  --header 'X-API-KEY: <api-key>' \
  --data '
{
  "model_name": "<string>",
  "input_params": "<unknown>",
  "webhook_url": "<string>"
}
'

201

{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "model_name": "<string>",
  "gen_type": "<string>",
  "failed_reason": "<string>",
  "assets": "<string>",
  "input_params": "<unknown>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "status": "initializing",
  "aspect_ratio": "<string>",
  "output_nums": -1,
  "duration": -1,
  "resolution": "<string>",
  "webhook_url": "<string>"
}

Supported models and Pricing

The following models are available for asset generation.
Each model includes its name, generation type and pricing.

Pricing below is per output (e.g. per video or per image).
If a model supports multiple outputs (like num_images), total cost = per-output price × number of outputs.

Model name	Generation type	Pricing
kling-video/v1.6/pro/image-to-video	image_to_video	Duration 5 seconds → 12 credits Duration 10 seconds → 24 credits
kling-video/v1.6/pro/text-to-video	text_to_video	Duration 5 seconds → 12 credits Duration 10 seconds → 24 credits
veo3.1/image-to-video	image_to_video	64 credits per output
veo3.1	text_to_video	Duration 4 seconds → 32 credits Duration 6 seconds → 48 credits Duration 8 seconds → 64 credits
veo3.1/first-last-frame-to-video	image_to_video	64 credits per output
flux-pro/kontext/text-to-image	text_to_image	4 credits per output
flux-pro/kontext/max/multi	image_to_image	4 credits per output
veo3.1/fast	text_to_video	Duration 4 seconds → 16 credits Duration 6 seconds → 24 credits Duration 8 seconds → 32 credits
veo3.1/reference-to-video	image_to_video	64 credits per output
nano-banana	text_to_image	4 credits per output
nano-banana/edit	image_to_image	4 credits per output
kling-video/v2.1/master/text-to-video	text_to_video	Duration 5 seconds → 40 credits Duration 10 seconds → 80 credits
veo3.1/fast/image-to-video	image_to_video	32 credits per output
wan-25-preview/text-to-image	text_to_image	4 credits per output
wan-25-preview/image-to-image	image_to_image	4 credits per output
wan-25-preview/text-to-video	text_to_video	Duration 5s @ 480p → 8 credits Duration 5s @ 720p → 12 credits Duration 5s @ 1080p → 16 credits Duration 10s @ 480p → 16 credits Duration 10s @ 720p → 24 credits Duration 10s @ 1080p → 32 credits
veo3.1/fast/first-last-frame-to-video	image_to_video	32 credits per output
flux-pro/v1.1-ultra	text_to_image	4 credits per output
flux-pro/v1.1-ultra/redux	image_to_image	4 credits per output
kling-video/v2.1/master/image-to-video	image_to_video	Duration 5 seconds → 40 credits Duration 10 seconds → 80 credits
sora-2/text-to-video	text_to_video	Duration 4 seconds → 8 credits Duration 8 seconds → 16 credits Duration 12 seconds → 24 credits
bytedance/seedream/v4/edit	image_to_image	4 credits per output
bytedance/seedream/v4/text-to-image	text_to_image	4 credits per output
wan-25-preview/image-to-video	image_to_video	Duration 5s @ 480p → 8 credits Duration 5s @ 720p → 12 credits Duration 5s @ 1080p → 16 credits Duration 10s @ 480p → 16 credits Duration 10s @ 720p → 24 credits Duration 10s @ 1080p → 32 credits
sora-2/text-to-video/pro	text_to_video	Duration 4s @ 720p → 24 credits Duration 4s @ 1080p → 40 credits Duration 8s @ 720p → 48 credits Duration 8s @ 1080p → 80 credits Duration 12s @ 720p → 72 credits Duration 12s @ 1080p → 120 credits
bytedance/seedance/v1/pro/image-to-video	image_to_video	Duration 5s @ 480p → 8 credits Duration 5s @ 720p → 8 credits Duration 5s @ 1080p → 16 credits Duration 10s @ 480p → 16 credits Duration 10s @ 720p → 16 credits Duration 10s @ 1080p → 32 credits
bytedance/seedance/v1/pro/text-to-video	text_to_video	Duration 5s @ 480p → 8 credits Duration 5s @ 720p → 8 credits Duration 5s @ 1080p → 16 credits Duration 10s @ 480p → 16 credits Duration 10s @ 720p → 16 credits Duration 10s @ 1080p → 32 credits
sora-2/image-to-video	image_to_video	Duration 4 seconds → 8 credits Duration 8 seconds → 16 credits Duration 12 seconds → 24 credits
sora-2/image-to-video/pro	image_to_video	Duration 4s @ 720p → 24 credits Duration 4s @ 1080p → 40 credits Duration 8s @ 720p → 48 credits Duration 8s @ 1080p → 80 credits Duration 12s @ 720p → 72 credits Duration 12s @ 1080p → 120 credits
veo3/fast	text_to_video	Duration 4s → 20 credits Duration 6s → 32 credits Duration 8s → 40 credits
veo3/fast/image-to-video	image_to_video	40 credits per output
minimax/hailuo-02/standard/text-to-video	text_to_video	Duration 6 seconds → 12 credits Duration 10 seconds → 24 credits
minimax/hailuo-02/standard/image-to-video	image_to_video	Duration 6 seconds → 12 credits Duration 10 seconds → 24 credits
minimax/hailuo-02/pro/text-to-video	text_to_video	20 credits per output
minimax/hailuo-02/pro/image-to-video	image_to_video	20 credits per output

Model Input Parameters (input_params)

Each model has its own unique input parameters. Select a model below to view its required fields, optional fields, and full JSON Schema.

kling-video/v1.6/pro/image-to-video

kling-video/v1.6/pro/image-to-video

Field	Type	Required	Description	Allowed values	Default
prompt	string	Yes	Description of the video content.	–	–
image_url	string	Yes	URL of the starting image.	–	–
duration	string	No	Duration in seconds.	5, 10	5
aspect_ratio	string	No	Generated video aspect ratio.	16:9, 9:16, 1:1	16:9
cfg_scale	number	No	How strictly model follows the prompt.	0–1 (0.1 step)	0.5
tail_image_url	string	No	Optional ending image.	–	–
negative_prompt	string	No	Things to avoid in the output.	–	"blur, distort..."

example-model-x

example-model-x

Field	Type	Required	Description
prompt	string	Yes	Description of the image.
steps	number	No	Number of generation steps.

Authorizations

X-API-ID · string · header · required

API ID, from your settings page.

X-API-KEY · string · header · required

API Key, from your settings page.

Body

model_name · string · required

Name of the AI generation model.

Maximum string length: 255

input_params · any · required

Parameters for generation

webhook_url · string<uri>

Webhook URL

Response

201 - application/json

id · string<uuid> · required

model_name · string · required

Name of the AI generation model used.

gen_type · string · required

Type of the AI generation model used.

failed_reason · string · required

Reason for failure if the generation failed.

assets · string · required

List of generated assets.

input_params · any · required

Input parameters used for AI generation.

created_at · string<date-time> · required

updated_at · string<date-time> · required

status · enum<string>

• initializing - initializing
• generating - generating
• done - done
• failed - failed

Available options: initializing, generating, done, failed

aspect_ratio · string | null

Aspect ratio of the asset

Maximum string length: 128

output_nums · integer

Number of outputs

Required range: -2147483648 <= x <= 2147483647

duration · integer | null

Video duration in seconds

Required range: -2147483648 <= x <= 2147483647

resolution · string | null

e.g., 1080x1920

Maximum string length: 128

webhook_url · string<uri> | null

Webhook URL for status updates. Default is null.

Maximum string length: 200