Kling 4.0 is Kuaishou's next-generation AI video model. It is designed for longer, more coherent scenes with multi-keyframe direction, multimodal references, complex motion, synchronized audio, and high-dynamic-range output.

When will Kling 4.0 be available in PhotoGPT?

Kling announced the full model for an October 2026 release. PhotoGPT model-specific creation will become available after the model and integration are ready.

How long can Kling 4.0 videos be?

Kling has announced native video generation up to 30 seconds, giving a scene more room to establish, develop, and resolve without stitching together several short clips.

How many references can Kling 4.0 use?

Kling has announced support for up to 15 multimodal references in one request, with ceilings of 10 images, 5 videos, and 7 subjects. References can guide characters, products, environments, style, and motion.

What do Kling 4.0 keyframes control?

Up to 10 keyframes can define important visual states the video should pass through. This gives creators more control over the sequence of a shot, not only its opening and closing frames.

Does Kling 4.0 generate audio?

Kling announced high-quality stereo audio with improved lip synchronization and support for several languages, dialects, and accents. Exact options in PhotoGPT will depend on the final integration.

What resolution does Kling 4.0 support?

Kling announced 4K and 1080p output with 10-bit HDR color and 21:9 framing as rollout capabilities. Actual resolutions and aspect ratios in PhotoGPT will depend on model availability and integration support.

Kling 4.0 announcement · Full model planned for October 2026

KLING 4.0

Start with a scene or an image. Describe the action, camera movement, and style, then create your video in PhotoGPT.

Direct the whole story

Build coherent 30-second scenes with controlled keyframes, consistent characters and products, complex camera movement, synchronized stereo sound, and professional visual detail.

Explore AI video generation

WHY KLING 4.0

More story. More control. Less stitching.

Kling 4.0 doubles Kling 3's announced maximum native duration from 15 to 30 seconds, then combines keyframe control, multimodal references, and more finishing headroom for a complete scene.

Native generation: 30 secA full campaign beat or long take in one output
Keyframes: 10Place the visual states the story must pass through
Multimodal references: 15Coordinate subjects, products, style, and motion
Announced delivery: 4K HDR10-bit color and 21:9 framing are rollout capabilities

Long-form storytelling

Tell a complete story in 30 seconds

Give a reveal, performance, or campaign beat room to establish, develop, and resolve in one native generation instead of stitching together several short clips.

Multi-keyframe direction

Direct the scene with up to 10 keyframes

Set the important visual states your shot should pass through. Guide character action, scene changes, composition, and timing across the full sequence.

Omni Reference

Keep every reference working together

Combine up to 15 multimodal references for characters, products, locations, style, and motion so the creative brief stays recognizable from shot to shot.

Native audiovisual generation

Bring performance and sound into sync

Create expressive dialogue and movement with announced improvements to lip synchronization, stereo sound, and support for multiple languages, accents, and dialects.

Targeted video editing

Refine the shot without starting over

Adjust selected characters, backgrounds, movement, or visual style while preserving the surrounding scene and the parts that already work.

Prompting Kling 4.0

See how text, reference inputs, storyboards, and edit instructions each shape a Kling 4.0 scene

Duration & place

A 7-second shot set in the UK fixes the length and setting first.

Action order

Recognise, approach, then embrace spells the reunion out as a sequence.

Camera

Handheld follow with subtle shake keeps the viewpoint warm, not frantic.

Look & sound

Warm light, footsteps, and dialogue finish the scene together.

Text & Dialogue

Kling 4.0 Prompting Guide

MODEL COMPARISON

Kling 3.0 vs Kling 4.0

Kling 3.0 established longer multi-shot creation with native audio and 4K workflows. Kling 4.0 expands the directing surface with twice the duration, more keyframes, broader references, and HDR delivery.

Maximum duration: Kling 3.0Flexible 3–15 seconds; Kling 4.0Up to 30 seconds
Scene direction: Kling 3.0Start/end frames and custom multi-shot; Kling 4.0Up to 10 keyframes across the sequence
Reference workflow: Kling 3.0Image and element references in supported workflows; Kling 4.0Up to 15 image, video, and subject references
Native audio: Kling 3.0Multilingual dialogue, sound, and lip sync; Kling 4.0Stereo audio with improved lip sync and voice support
Delivery: Kling 3.0Up to native 4K in supported workflows; Kling 4.04K and 1080p with announced 10-bit HDR

Comparison of the announced capabilities of Kling 3.0 and Kling 4.0
Capability	Kling 3.0	Kling 4.0
Maximum duration	Flexible 3–15 seconds	Up to 30 seconds
Scene direction	Start/end frames and custom multi-shot	Up to 10 keyframes across the sequence
Reference workflow	Image and element references in supported workflows	Up to 15 image, video, and subject references
Native audio	Multilingual dialogue, sound, and lip sync	Stereo audio with improved lip sync and voice support
Delivery	Up to native 4K in supported workflows	4K and 1080p with announced 10-bit HDR

KLING 4.0 PREVIEW

Direct more. Stitch less.

Plan a complete 30-second scene, guide its most important moments with keyframes, and coordinate character, product, environment, motion, and sound references before generation. While Kling 4.0 and the PhotoGPT integration roll out, start shaping your creative brief in PhotoGPT's video studio.

Up to 30-second native generationUp to 10 directed keyframesUp to 15 multimodal referencesSynchronized stereo audioAnnounced 4K HDR delivery

Explore AI video generation

Subscription Plans

Explore current PhotoGPT plans. Kling 4.0 availability and pricing will be added after integration.

Starter

For getting started

$16.66~~$19.99~~

per month · billed $99.99 every 6 months

5,000credits

per month · ≈ 500 AI images

Up to 3 model trainings per month

5,000 shared credits per month
Use credits for up to 92 Nano Banana Pro images or 142 GPT Image 2 medium images
Create up to 13 Seedance 2, 11 Kling 3.0 Pro, or 14 Grok Imagine clips (5 sec)
Generate up to 500 standard AI images and AI photos every month
Refine up to 500 photos with AI editing every month
Starter credit pool for lighter AI video, editing, and upscaling projects

Hobby

For regular creators

$24.99~~$33.32~~25% off sale

per month · billed $149.99 every 6 months

9,000credits

per month · ≈ 900 AI images

Up to 6 model trainings per month

Everything in Starter, plus 4,000 additional credits per month
Added credits alone cover 2 model trainings, 74 Nano Banana Pro images, or 114 GPT Image 2 medium images
Or 10 extra Seedance 2, 9 extra Kling 3.0 Pro, or 11 extra Grok Imagine clips (5 sec)
Generate up to 900 standard AI images and AI photos every month
Refine up to 900 photos with AI editing every month
More credits for regular AI video, PhotoGPT Flow, and upscaling workflows

Most Powerful

Pro

For power users

$33.33~~$44.44~~25% off sale

per month · billed $199.99 every 6 months

16,000credits

per month · ≈ 1600 AI images

Up to 10 model trainings per month

Everything in Hobby, plus 7,000 additional credits per month
Added credits alone cover 4 model trainings, 129 Nano Banana Pro images, or 200 GPT Image 2 medium images
Or 18 extra Seedance 2, 16 extra Kling 3.0 Pro, or 19 extra Grok Imagine clips (5 sec)
Generate up to 1600 standard AI images and AI photos every month
Refine up to 1600 photos with AI editing every month
Largest credit pool for frequent MiniMax Hailuo H3, Google Omni, Grok Imagine Video 1.5, Seedance 2.0, Veo 3.1, Kling 3.0, and 4K video production

Included with every plan

Credits work across AI images, AI videos, model training, editing, upscaling, and PhotoGPT Flow.

AI video generation with MiniMax Hailuo H3, Google Omni, Grok Imagine Video 1.5, Seedance 2.0, Veo 3.1, and Kling 3.0 (including 4K)
AI image editing, background changes, retouching, and image upscaling
PhotoGPT Flow for connected image, video, and editing workflows
100+ AI presets, text-to-image generation, prompt assistance, and top-up credits

Frequently asked questions

Start Exploring

Join our Discord community of 1000s of active users, get insights on latest prompt ideas and explore community generations

Generate Videos Join Discord

Google Veo 3.1 Seedance 2