Kling V2 New / 画像生成
Updated iteration of the V2.0 series image generation model. Retains core multi-reference capabilities—character, face, subject, scene, and style—with refined performance optimizations. Supports diverse aspect ratios and reference-based generation for consistent visual output
Kling V2 NewReference-Locked Image Editing
Kling V2 New focuses on image-to-image editing with subject or face reference lock, negative prompts, and multi-ratio output — built for consistent product and character variants.
Editing-First Image Workflow
Start from an existing still and iterate with identity locked.
Required Image Conditioning
Every generation starts from a source image — ideal for restyling, recomposing, and variant production.
Identity Lock Modes
Switch between subject and face reference so talent or product identity stays stable across edits.
Negative Prompt Steering
Exclude backgrounds, props, or styles you do not want while keeping the source composition intact.
Ratio Coverage
Export to 1:1, 16:9, 4:3, 3:2, 2:3, 3:4, 9:16, and 21:9 without re-cropping by hand.
How It Works
A production-ready path from brief to finished asset.
Upload Source Still
Every generation starts from your existing image — the edit base.
Set Identity Lock
Choose subject or face lock so talent/product identity survives the edit.
Describe the Change
State the new background, style, or prop change. Keep the brief surgical.
Export Channel Ratios
Generate the aspect ratios you need without hand-cropping after the fact.
Editing Production Domains
Where every output is a refined variant.
Variant Production
Multiple ratios and styles from one packshot.
Character Consistency
Face-locked edits across campaign assets.
Background Swap
Recompose subjects into new environments.
Catalog Refresh
Seasonal restyles without reshooting.
Prompt & Usage Tips
Practical guidance for reliable first-pass results.
Single-change prompts (new background OR new style) keep identity more stable.
Exclude extra props or messy backgrounds that the source may introduce.
V2 New is 1K-focused. Switch to Kling V2 when 2K masters are required.
I2I Editing Quickstart
Edit an existing still with identity locked.
curl -X POST "https://api.powertokens.ai/v1/images/generations" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type": "application/json" \
-d '{
"model": "kling-v2-new",
"prompt": "Editorial close-up portrait with sculptural hat, photorealistic studio light.",
"size": "1k",
"response_format": "url",
"watermark": false,
"aspect_ratio": "16:9"
}'Technical Specifications
Confirmed parameters and runtime execution protocols.
料金詳細
このモデルの実際の課金は、API リクエストで渡される特定のパラメータに基づいて動的に計算されます。以下は具体的な組み合わせとそれに対応する料金です：
| モダリティ | クレジット | 料金 (USD) |
|---|---|---|
| Image to Image | 28/ Image | $0.028 |
Models from the Same Channel
Explore complementary models and alternative versions from the same provider channel.
Kling Image O1
kling-image-o1
Advanced image generation model from the Kling O1 family. Supports text-to-image and image-to-image workflows with deep semantic understanding. Features character/subject consistency across generations, multi-reference input (up to 7 images), and intelligent aspect ratio adaptation. Professional-grade output suitable for commercial creative pipelines
Kling V2
kling-v2
V2.0 foundational image model supporting text-to-image and image-to-image generation. Enables multi-type reference control—character, face, subject, scene, and style. Built for role consistency and thematic control across generated visuals. Multiple aspect ratio support
Recommended Related Models
Explore complementary video and multimodal models with your unified API key.
Seedream 5.0
seedream-5-0-260128
Supports text, single-image and multi-image inputs, and enables the generation of image sets
Wan 2.7 Image Pro
wan2.7-image-pro
Wan2.7–image-pro，supports text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following.
Qwen Image 2.0 Pro
qwen-image-2.0-pro
The full-featured Qwen-Image-2.0 series models integrate image generation and image editing, offering enhanced text rendering with support for 1,000-token prompts, more refined realistic textures, detailed depiction of photorealistic scenes, and stronger semantic adherence. The full-featured version delivers the strongest text rendering and most lifelike textures in the 2.0 series.
MiniMax Image-01
image-01
MiniMax’s first text-to-image model with subject reference support. Delivers high-fidelity visuals, detailed lighting, and complex scene composition. Generates realistic human/object renders with natural textures, ideal for concept art, product visualization, and creative design.
Frequently Asked Questions
Everything you need to know before integrating this model.
Start Building with Kling V2 New Today
Create an account in seconds to receive 100 free credits and start generating immediately. No credit card or upfront contract required.