Kling O1 Image Edit API

kwaivgi/kling-image-o1

1K / 2K · 3.5 credits/image (≈ $0.018)

Kling O1 Image Edit transforms and refines visual imagery using up to 10 reference images alongside natural language instructions, featuring multi-reference feature synthesis, mask-free surgical local edits, and native aspect ratio inheritance. It carries out complex wardrobe modifications, background transfers, and asset insertions while strictly preserving subject identity, facial contours, and authentic lighting textures.

Get API Key

Input

Prompt

909/2000

Image Urls

2/10

Add images

Elements

Reference subjects in order with @Element1, @Element2. Provide a main view and additional views. Sign in to upload files.

Size

Resolution

Output Format

OutputReady

Continue with

Kling O3 Image Kling 3.0 Turbo Kling 2.6

Examples

Use image 1 as the flooded forest boardwalk scene to edit and image 2 only as the animal identity reference. Edit the scene in image 1 by adding exactly one adult Malayan tapir, the tapir from image 2, standing on the wide wooden deck in the left-center foreground. Preserve the exact tapir identity and anatomy from image 2: black head, neck and hindquarters, broad white saddle, short flexible snout and white-rimmed ears. The tapir faces left in three-quarter side view, pausing as if listening toward the flooded forest. Its full body must be visible, four feet planted naturally on the boardwalk, correct real-world scale, weight and soft contact shadows. Preserve the boardwalk structure, tree positions, floodwater reflections, original camera perspective and documentary photographic style. Match the soft green canopy daylight. Do not add people, other animals, accessories, text, logos or watermark.

Make one precise localized edit to this documentary photograph: change only the faded blue canvas messenger bag and its shoulder strap into worn warm-brown leather. Preserve the exact bag silhouette, flap, size, position at the man's right hip, strap route and existing perspective. Add believable leather grain, subtle creases and gently polished worn edges; keep the design plain and unbranded. Everything else must remain unchanged: the same man's face, skin tone, shaved head, expression, pose, hands, dark fleece jacket, trousers, boots, black headphones, handheld recorder, camera framing, salt-crystal cavern geometry, lighting and shadows. Do not add or remove objects, people or animals. No text, logos or watermark.

Transform this rooftop rainwater-collection photograph into a detailed hand-carved two-color woodcut print, using deep indigo and warm terracotta ink on warm ivory paper. Preserve the original camera view and spatial composition exactly: two cylindrical tanks side by side on the left, the sloping corrugated roof at upper left, downpipe feeding the left tank, connector between the tanks, descending outlet, low brick parapet, drain grate at right foreground, and distant apartment skyline. Keep all pipes connected plausibly and each original object recognizable. Translate shading into expressive carved hatching, bold clean silhouettes, slightly imperfect ink edges and subtle paper texture; no photographic gradients. One continuous scene, no borders, panels, diagrams, added objects, people, animals, text, labels, branding or watermark.

REST API

Quick Start

This flow submits one valid Kling O1 Image request, captures its task_id, and reads image URLs after the asynchronous task ends.

Connect to the Vidgo API

Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one image task

Send the current model ID, prompt, and ordered image URLs to the unified submit endpoint. The example keeps only first-call fields.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "kwaivgi/kling-image-o1",
  "input": {
    "prompt": "Use image 1 as the flooded forest boardwalk scene to edit and image 2 only as the animal identity reference. Edit the scene in image 1 by adding exactly one adult Malayan tapir, the tapir from image 2, standing on the wide wooden deck in the left-center foreground. Preserve the exact tapir identity and anatomy from image 2: black head, neck and hindquarters, broad white saddle, short flexible snout and white-rimmed ears. The tapir faces left in three-quarter side view, pausing as if listening toward the flooded forest. Its full body must be visible, four feet planted naturally on the boardwalk, correct real-world scale, weight and soft contact shadows. Preserve the boardwalk structure, tree positions, floodwater reflections, original camera perspective and documentary photographic style. Match the soft green canopy daylight. Do not add people, other animals, accessories, text, logos or watermark.",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-image-o1/edit/v1/01/input-01.png",
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-image-o1/edit/v1/01/input-02.png"
    ],
    "resolution": "2K",
    "size": "16:9",
    "output_format": "png",
    "n": 1
  }
}'

Wait for the image result

Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "G9UB0VC3IRIBRX9W",
    "status": "running",
    "created_time": "2026-09-24T11:52:39"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "G9UB0VC3IRIBRX9W",
    "status": "finished",
    "files": [
      {
        "file_url": "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-image-o1/edit/v1/01/output.png",
        "file_type": "image"
      }
    ],
    "created_time": "2026-09-24T11:52:39",
    "error_message": null,
    "progress": 100
  }
}

Complete runnable polling example

Expand for the same payload end to end, including business-code, missing-task-ID, failed-state, unexpected-state, and network-error handling.

Complete runnable polling example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "kwaivgi/kling-image-o1",
  "input": {
    "prompt": "Use image 1 as the flooded forest boardwalk scene to edit and image 2 only as the animal identity reference. Edit the scene in image 1 by adding exactly one adult Malayan tapir, the tapir from image 2, standing on the wide wooden deck in the left-center foreground. Preserve the exact tapir identity and anatomy from image 2: black head, neck and hindquarters, broad white saddle, short flexible snout and white-rimmed ears. The tapir faces left in three-quarter side view, pausing as if listening toward the flooded forest. Its full body must be visible, four feet planted naturally on the boardwalk, correct real-world scale, weight and soft contact shadows. Preserve the boardwalk structure, tree positions, floodwater reflections, original camera perspective and documentary photographic style. Match the soft green canopy daylight. Do not add people, other animals, accessories, text, logos or watermark.",
    "image_urls": [
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-image-o1/edit/v1/01/input-01.png",
      "https://cdn.vidgo.ai/apis/models/kwaivgi/kling-image-o1/edit/v1/01/input-02.png"
    ],
    "resolution": "2K",
    "size": "16:9",
    "output_format": "png",
    "n": 1
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

This table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.

Field	Type	Required	Default	Description
input.prompt	string	Yes	–	String, 1–2,000 characters after trimming.
input.image_urls	string[]	Yes	–	1–10 public HTTP(S) image URLs, passed in order.
input.resolution	string	No	1K	Output resolution; 1K and 2K have the same rate. 1K, 2K
input.size	string	No	auto	Output aspect ratio. Default: auto. auto, 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9
input.output_format	string	No	png	Output image format. jpeg, png, webp
input.n	integer	No	1	Integer output count, 1–9. Total credits = the resolution rate × n.
input.elements	object[]	No	–	Array of subject-reference objects. Reference them as @Element1, @Element2, etc. No published count limit; extension fields are preserved.
input.elements[].frontal_image_url	string	No	–	Public HTTP(S) URL for the main subject view.
input.elements[].reference_image_urls	string[]	No	–	Array of public HTTP(S) image URLs for additional views of the same subject.

Response Fields

The submit response identifies the task. The status response supplies image files or failure details at a terminal state.

Field	Type	Description
code	integer	Business response code; 0 or 200 indicates success.
message	string	Optional human-readable response message.
data.task_id	string	Unique task ID used for status queries after submission.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp.
data.progress	integer	Progress from 0–100 in status responses.
data.files[]	array	Generated files in returned order when finished.
data.files[].file_url	string	Direct generated-image URL.
data.files[].file_type	string	Image results are identified as image.
data.files[].watermark_url	string \| null	Optional watermarked-file URL when present.
data.error_message	string \| null	Readable failure reason for failed tasks.

Task Lifecycle

Only the first two states may be polled again. finished and failed are terminal.

not_started
Accepted and queued; wait before checking again.
running
Image generation is in progress; continue polling.
finished
Successful terminal state; validate files and read image URLs.
failed
Failure terminal state; read error_message and stop.

Polling and Errors

Authentication401 means the key is missing or invalid. Fix authentication before resubmitting and never expose the key in browser code.
Validation400 indicates an invalid model ID, field, enum, length, or image count.
Polling intervalStart at 2–5 seconds, use exponential backoff for 429/5xx, and enforce an overall timeout.
Terminal statesStop after finished or failed. Treat finished without a valid image as a separate error.
Callback optionProvide a public top-level callback_url to receive a flat task object after finished or failed.
Network errorsDistinguish request timeout, network failure, and task failure. Retry the same query only when safe.

Model Specifications

Specification	Value	Details
Input mode	Prompt + 1–10 images	Supports optional subject elements.
Resolution	1K · 2K	Default: 1K.
Aspect ratio	auto, 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9	Default: auto.
Output format	jpeg · png · webp	Default: png.
Output count	1–9	Integer; default: 1.
Billing	1K/2K: 3.5 credits/image (approximately $0.018). Total credits = 3.5 × n, without reference-image or subject-reference surcharges. At $0.005 per credit, one image costs $0.0175. Round USD to three decimals after calculating the total.	1 credit = $0.005. USD is displayed to three decimals; final billing is determined by the backend.

Kling O1 Image API documentation

Kling O1 Image Edit Overview

Kling O1 Image Edit is a unified multimodal image editing and synthesis model developed by Kuaishou (Kling AI). Built on the Multi-modal Visual Language (MVL) architecture, it accepts 1 to 10 reference images and delivers high-dimensional feature disentanglement, mask-free natural-language local repainting, auto aspect ratio preservation, and direct high-definition outputs up to 2K. It empowers e-commerce staging, creative composites, and serial character consistency without complex manual masking.

Why Choose Kling O1 Image Edit?

High-Dimensional Multi-Image SynthesisIngests up to 10 reference images simultaneously, intelligently decomposing subject identity, composition lines, artistic palettes, and textural cues into an organic, harmonious visual composite.
Mask-Free Natural-Language InpaintingEliminates manual brushwork and region masking. Plain text descriptions guide surgical alterations across apparel, accessories, lighting, and backgrounds while leaving surrounding pixels untouched.
Adaptive Auto Aspect RatioFeatures an auto framing option that matches the dimensions of your source image, alongside 8 standard aspect ratios with perspective-aware perimeter extensions.
Persistent Identity and Lighting RetentionFirmly anchors facial anatomy, unique materials, and ambient highlights during background replacements or character migrations, ensuring visual asset consistency across iterations.
Transparent Pricing with Zero Input FeesBilled at a flat rate of 3.5 credits per output image (approx. $0.018) across both 1K and 2K resolutions, with no surcharges for input images or subject elements, backed by automatic refunds for failed tasks.

Parameters

Parameter	Requirement	Description
prompt	Required	String, 1–2,000 characters after trimming.
image_urls	Required	1–10 public HTTP(S) image URLs, passed in order.
resolution	Optional	Output resolution; 1K and 2K have the same rate. Default`1K2K`
size	Optional	Output aspect ratio. Default: auto. Default`auto16:99:161:14:33:43:22:321:9`
output_format	Optional	Output image format. Default`pngjpegwebp`
n	Optional	Integer output count, 1–9. Total credits = the resolution rate × n. Default`1`
elements	Optional	Array of subject-reference objects. Reference them as @Element1, @Element2, etc. No published count limit; extension fields are preserved.
elements[].frontal_image_url	Optional	Public HTTP(S) URL for the main subject view.
elements[].reference_image_urls	Optional	Array of public HTTP(S) image URLs for additional views of the same subject.

How to Use

Prepare Visual ReferencesCollect 1 to 10 publicly accessible HTTP(S) image URLs featuring character portraits, products, background environments, or aesthetic references.
Draft Clear Modification InstructionsFormulate concise prompts specifying modifications alongside preserved regions (e.g., "Keep the model's face and pose from image 1, wear the blazer from image 2, and maintain the original studio background").
Select Aspect Ratio and ResolutionSet size to auto to inherit source proportions or pick a standard ratio (e.g., 16:9, 1:1), then choose 1K or 2K resolution.
Define Format and Output CountChoose your delivery format (PNG, JPEG, or WebP) and configure the image generation count n between 1 and 9.
Submit Task and Retrieve AssetsDispatch the request to the asynchronous API and collect final high-definition image assets via status polling or webhook notifications.

Pricing

1K/2K: 3.5 credits/image (approximately $0.018). Total credits = 3.5 × n, without reference-image or subject-reference surcharges. At $0.005 per credit, one image costs $0.0175. Round USD to three decimals after calculating the total.

Usage	Rate	Details
1K / 2K Edit	3.5 credits/image · ≈ $0.018	Multiply by output count n; 2 images = 7 credits ($0.035).

Best Use Cases

E-Commerce Virtual Try-On and StagingSeamlessly merge studio model portraits with garment flats and realistic background environments with cohesive shadows.
Multi-Angle Character ConsistencyRecombine multiple reference photos of varied expressions into uniform character portraits across novel poses and settings.
Adaptive Visual Re-FramingRetain native proportions with auto or intelligently extend horizontal key visuals into 9:16 vertical social banners without distortion.
Surgical Asset Editing and Object RemovalAdd or remove props, alter hairstyles and hair colors, or replace cluttered backdrops with clean studio sets effortlessly.

Pro Tips

When supplying multiple references, disambiguate them clearly in your prompt (e.g., "Combine the facial traits of image 1 with the leather jacket styling from image 2").
Explicitly state boundaries between what changes and what stays static (e.g., "Replace the handbag with a paper coffee cup, preserving posture, facial expression, and lighting").
Use size: "auto" to automatically conform the output to the exact aspect ratio of the first input image.
High-clarity, well-lit reference images improve the accuracy of feature extraction and boundary preservation.

Notes

image_urls is required and must contain an array of 1 to 10 valid public HTTP(S) image URLs.
prompt is required and must span 1 to 2,000 characters after trimming whitespace.
Output count n must be an integer between 1 and 9; billing scales with n with no additional fees for reference images.
Task execution is asynchronous; monitor progress via task_id polling or set a callback_url for automatic webhooks.

Related Models

Qwen Image 3.0 Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Text-to-Image preview

Qwen Image 3.0 Pro Text-to-ImageAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Qwen Image 3.0 Pro Image EditAlibaba Qwen Image 3.0 Standard and Pro generation and editing with eight aspect ratios, 1K or 2K output, and ordered one-to-three-image editing.

Seedream 5.0 Pro Text-to-ImageThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

Seedream 5.0 Pro Image EditThe ByteDance Seedream 5.0 Pro API generates 1K or 2K JPEG/PNG images from prompts and edits one to ten ordered HTTP(S) image inputs.

GPT Image 2 Text-to-ImageOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

GPT Image 2 Image EditOpenAI image generation and editing with quality tiers, flexible size controls, and single-image outputs up to 4K.

Nano Banana 2 Text-to-ImageGoogle's next-gen image model powered by Gemini 3.1 Flash with native 2K/4K resolution, chain-of-thought reasoning, precise multi-language text rendering, and up to 14 reference images.

Nano Banana 2 Image EditGoogle's next-gen image model powered by Gemini 3.1 Flash with native 2K/4K resolution, chain-of-thought reasoning, precise multi-language text rendering, and up to 14 reference images.

Nano Banana Pro Text-to-ImageGoogle's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing.

Nano Banana Pro Image EditGoogle's Nano Banana Pro image model powered by Gemini 3 Pro for 4K generation, strong text rendering, multi-image blending, and production-ready image editing.

GPT Image 1.5OpenAI's latest image model with 4x speed, precision editing, and superior text rendering.

Z-ImageAlibaba's efficient 6B-parameter image model with sub-second generation and exceptional Chinese-English bilingual text rendering capabilities.

Seedream 4.5ByteDance's unified 4K image generation and editing model with professional-grade text rendering and commercial photography quality.

Seedream 5.0 LiteByteDance Seedream 5.0 Lite family on Vidgo API: seedream-5.0-lite for text-to-image and seedream-5.0-lite-edit for image-to-image editing, with 2K/3K presets, custom sizes, and up to 10 reference images.

Kling O1 Image Edit API frequently asked questions

What is the Kling O1 Image Edit API?

Kling O1 Image Edit is a state-of-the-art multimodal image editing and multi-reference synthesis model developed by Kuaishou (Kling AI). It refines and blends imagery using 1 to 10 reference images and natural language instructions, featuring multi-source feature synthesis, mask-free surgical local edits, auto aspect ratio inheritance, and high-definition output up to 2K. Built on the unified Multi-modal Visual Language (MVL) architecture, it preserves subject facial geometry, original material textures, and environmental lighting while performing seamless wardrobe swaps, scene transfers, or object edits. You can call it programmatically or try it from the playground above.

How many reference images does Kling O1 Image Edit support in a single request?

It accepts between 1 and 10 publicly accessible HTTP(S) image URLs. The engine concurrently analyzes character identities, color palettes, compositions, and prop details across multiple inputs, blending them harmoniously into a unified visual result.

How does Kling O1 Image Edit preserve subject identity and lighting during local edits?

The model leverages semantic region localization without manual masking. By explicitly detailing modifications and unaffected zones in the prompt, the architecture localizes transformations within feature space, retaining the original facial contours, skin textures, and specular reflections intact.

Does Kling O1 Image Edit support preserving the original aspect ratio?

Yes. Setting the size parameter to auto instructs the model to detect and inherit the exact aspect ratio of the primary reference image; developers can also select from 8 standard presets with seamless ambient scene extension.

Does Kling O1 Image Edit charge extra fees for uploaded reference images?

No. Kling O1 Image Edit uses a flat rate of 3.5 credits (approx. $0.018) per output image with zero surcharges for reference inputs. Charges are calculated solely on the number of generated images, and interrupted tasks are automatically refunded in full.

What resolutions and output image formats does Kling O1 Image Edit support?

It supports 1K and 2K output resolutions at identical rates, delivering crisp results in PNG, JPEG, or WebP formats (PNG by default), even across intricate multi-source repainting tasks.

What is the recommended prompt structure for multi-image editing in Kling O1 Image Edit?

Structure prompts with clear directives: target subject + reference source index + desired action + preservation boundaries (e.g., "Take the character from image 1, dress them in the black trench coat from image 2, place them in the city street from image 3, and keep facial features and eye contact completely unchanged").