kling/kling-v2-i2i

Docs
Schema

[Core Function] Kling V2 I2I is an older generation image-to-image editing model. [Strengths] Offered improved multi-subject tracking and better texture details over V1. Maintained for backward compatibility. [Best For] Existing legacy integrations and workflows that strictly depend on this specific model version's quirks. [Limitations] Do NOT use this for new creations. It is a legacy model maintained for backward compatibility. [Routing] Only use if explicitly requested; otherwise use Kling V3 I2I.

$0.0320/img
image-to-image

Input

Image description text, supports Chinese and English
Reference image (Base64 encoded or URL). Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB
Hint: Drag and drop files, paste from clipboard (Ctrl/Cmd+V), or provide a URL.
Image aspect ratio
16:9
Image facial reference strength. Higher values mean stronger reference. Range: 0.0-1.0
Number of images to generate per request
Image resolution. V2 I2I only supports 1K (note: T2I supports 2K)
1k

Result

No results yet

Run the model to preview the output here.

Next:

README

Parameters

Name Description Type Required Enums
prompt Image description text, supports Chinese and English string Yes -
image Reference image (Base64 encoded or URL). Supported formats: .jpg, .jpeg, .png. Maximum size: 10MB string Yes -
aspect_ratio Image aspect ratio string No 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3, 21:9
image_fidelity Image facial reference strength. Higher values mean stronger reference. Range: 0.0-1.0 number No -
n Number of images to generate per request integer No -
resolution Image resolution. V2 I2I only supports 1K (note: T2I supports 2K) string No 1k

Pricing

Unit: $/img

Pricing
$0.0320/img