kling/kling-video-o1-i2v

Docs
Schema

[Core Function] Kling Video O1 I2V is the image-to-video slice of Kling O1 Omni Video. [Strengths] Reasoning-enhanced generation from 1-7 reference images, 720p/1080p, duration 3-10s (single image only 5 or 10). [Best For] Complex physical motion grounded in reference frames. [Limitations] No native audio; no aspect_ratio (follows first frame); duration capped at 10s. [Routing] Prefer this for O1-quality I2V; use Kling Video O1 V2V when a source video is required.

$0.0580~$0.0773/sec
image-to-video

Input

Video generation prompt.
Required reference images (max 7 when no reference video). With a single image, duration must be 5 or 10.
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Official O1 settings.audio without reference video: off only.
off
Video duration in seconds (3-10). With exactly one image, only 5 or 10 are allowed.
5
Output video resolution. Aspect ratio follows the first frame.
720p

Result

No results yet

Run the model to preview the output here.

Next:

README

Attributes

Parameters

Name Description Type Required Enums
prompt Video generation prompt. string Yes -
images Required reference images (max 7 when no reference video). With a single image, duration must be 5 or 10. string[] Yes -
audio Official O1 settings.audio without reference video: off only. string No off
duration Video duration in seconds (3-10). With exactly one image, only 5 or 10 are allowed. integer No 3, 4, 5, 6, 7, 8, 9, 10
resolution Output video resolution. Aspect ratio follows the first frame. string No 720p, 1080p

Pricing

Unit: $/sec

Dimension Pricing
resolution: 720p 0.0580
resolution: 1080p 0.0773