Kling O1 Image
What is Kling O1 Image?
Kling O1 Image is the image generation route under Kling O1. Same reference shape and prompt syntax as the O1 video endpoint, but the output is a still instead of a clip. Up to 10 reference images (image_urls), nine aspect ratios (Auto plus eight named ratios from square through 21:9), and 1K or 2K output. The reference cap, aspect ratios, and @image syntax match Kling 3.0 Omni Image; the only differences are the output ceiling at 2K (Omni Image goes to 4K) and the underlying generation. Use it to mock a composition with locked references before animating the same prompt in O1 video.
Key features of Kling O1 Image
Four features cover what production teams use the endpoint for.
Up to 10 reference images per call
Pass image_urls (max 10) and reference them in the prompt as @image_1 through @image_10. Useful for brand work where the brief locks character, product, environment, and palette references.
Nine aspect ratios including Auto
Auto picks the output aspect based on your references. The eight explicit options (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9) cover every standard placement.
1K or 2K output
Pick the resolution at the end of the cycle. 1K for fast iteration, 2K for delivery. For 4K stills, use Kling 3.0 Omni Image.
Reference shape matches Kling O1 video
Same image_urls cap and @image syntax as the O1 video endpoint, so a still composition you mock here can be animated in video with the same prompt and references.
Best for
Mock-then-animate workflows
Lock a composition in image with references, then animate the same prompt and references in Kling O1 video.
Heavy-reference image jobs
Up to 10 references per call. Useful for brand work with many fixed visual elements.
Cross-format design exploration
Different aspect presets from the same prompt and references. Useful for moodboards and pitch boards.
Story and character frames
Lock characters via consistent image references before motion work in O1 video.
Cost-controlled 2K delivery
2K output without paying the 4K rate. Good for most digital placements.
Use cases
Mock a campaign hero composition with 10 reference images locked (character, product, environment, brand palette), then animate the same prompt and references in Kling O1 video without rewriting the call. Run a moodboard pass for a brand pitch by holding the references constant and varying only the aspect ratio across the boards. Build a serial story with a recurring character by reusing the same image as @image_1 across multiple prompts. Render a 2K deliverable for digital placements without paying the 4K rate, with output coming back in the chosen aspect.
API examples
Call Kling O1 Image from any language by POSTing to /v1/tasks. Full parameter docs live at docs.unifically.com/models/image/kling/kling-omni-image.
curl -X POST https://api.unifically.com/v1/tasks \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "kuaishou/kling-o1-image",
"input": {
"prompt": "A serene mountain landscape at sunset, photorealistic",
"aspect_ratio": "16:9",
"resolution": "2k"
}
}'
Successful submission returns a task_id. Poll GET /v1/tasks/<task_id> or set a callback_url on the request to receive the finished result.
FAQs
People also ask
It is the image generation route under Kling O1. Generates stills from a prompt with optional reference images (image_urls, max 10), nine aspect ratios (Auto plus eight named ratios), and 1K or 2K output. Same reference syntax as the O1 video endpoint.
Nine total. Auto (the default, where the model picks based on references), 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, and 21:9.
Up to 10 entries in the image_urls array.
When the brief needs 4K output. O1 Image caps at 2K. The reference cap, aspect ratios, and prompt syntax are otherwise the same on both endpoints.
Same reference shape and prompt syntax as the O1 video endpoint. The image route returns a still instead of a clip. Useful for mocking compositions before generating motion in O1 video.