SandBase is live — $1 in free credits on signupStart free ›

KwaiVGI modelsimage generation api

kwaivgi/kling-image/o3/edit

Kling Image O3 Edit is KwaiVGI's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.

Input
Text prompt for image generation. Reference images using @Image1, @Image2, etc. (or @Image if only one image). Max 2500 characters.

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

List of reference images. Reference images in prompt using @Image1, @Image2, etc. (1-indexed). Max 10 images.
Image generation resolution. 1K: standard, 2K: high-res, 4K: ultra high-res. Allowed values: 1K, 2K, 4K.
The format of the generated image. Allowed values: jpeg, png.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
Idle

Example output — click Run to generate your own

API README

Kling Image O3 Edit

Kling Image O3 Edit is built for reworking existing imagery with written direction. One request can carry several reference images, and the prompt can address them individually as @Image1, @Image2, and onward when describing the transformation.

The edit is not locked to the source canvas: ten aspect ratios and 1K, 2K, or 4K rendering are exposed as output controls. PNG and JPEG options complete a workflow suited to substantial restyling, background changes, and other prompt-led reinterpretations.

Highlights

Multi-reference editing. Supply as many as ten images and identify each reference directly inside the prompt.

High-resolution reinterpretation. Render the transformed result at 1K, 2K, or 4K rather than inheriting a single fixed delivery size.

Flexible reframing. Choose among ten ratios when the edited composition must move between wide, square, and vertical formats.

PNG or JPEG output. Match the file format to an archival design asset or a lightweight preview.

Pricing

Billing unitPrice
Per request$0.028

When to Use

✅ Good fit❌ Consider alternatives
The model's named workflow matches the source material and intended outputA different input modality or model route is required
A managed asynchronous result is suitable for the production pipelineA synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or formatThe project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structureExact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverableEditable source layers or a native project file are required

Prompt Guide

For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "aspect_ratio": "21:9",
  "images": [
    "https://static.sandbase.ai/examples/kwaivgi/kling-image/o3/edit/output_url_0.png"
  ],
  "output_format": "png",
  "prompt": "Transform into photorealistic 3D render, add proper lighting and shadows, realistic materials and textures, maintain exact proportions and design from sketch, product visualization quality",
  "resolution": "1K"
}

Technical Specs

SpecValue
Model IDkwaivgi/kling-image/o3/edit
Inputsaspect_ratio, images, output_format, prompt, resolution
Required inputsprompt
Output fieldscontent_type, url
ExecutionAsync (submit, then poll for result)
Resolution1K / 2K / 4K
Aspect Ratio21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16
Output Formatjpeg / png

Related Models

Related Models

kwaivgi/kling-image/o3Kling Image O3 by KwaiVGI - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.kwaivgi/kling-image/o1Kling Image O1 by KwaiVGI - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.kwaivgi/kling-image/v3Kling Image V3 by KwaiVGI - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.kwaivgi/kling-image/v3/editKling Image V3 Edit is KwaiVGI's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.kwaivgi/kling-video/create-voiceKling Video Create Voice by KwaiVGI - advanced AI model for audio-to-audio. Delivers high-quality results with fast inference, suitable for both creative and production workflows.kwaivgi/kling-video/o1/pro/editKling Video O1 Pro is KwaiVGI's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.kwaivgi/kling-video/o1/pro/video-to-videoKling Video O1 Pro by KwaiVGI - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.kwaivgi/kling-video/o1/standard/editKling Video O1 Standard by KwaiVGI - AI-powered video editing and transformation. Apply style transfer, motion control, lip-sync, and visual effects to existing videos with natural language instructions.