Kling AI Video Models
Explore Kling AI video workflows for cinematic video generation, reference-driven motion control, native audio output and animated avatars, all on one flexible platform.

Kling 4.0
3–30-second storytelling with Omni Reference, up to 10 keyframes and output up to 4K.

Kling 4.0 Flash
Text, images and Omni Reference for 3–20-second, 720p video and frequent creative iteration.

Kling 3.0
Create 3–15-second videos from text or images with Kling 3.0. Shape character movement, camera work and native audio in one video workspace.

Kling 3.0 Turbo
Use Kling V3 Turbo to quickly generate high-quality text-to-video and image-to-video content, with precise audio-visual synchronization and cinematic visuals.

Kling O3
Create AI videos with Kling O3 using text, images and video references. Guide character appearance, scene details, movement and native audio from one workspace.

Kling 2.6
Bring an image into motion with Kling 2.6. Add a first frame, an optional end frame and a scene prompt to create 5- or 10-second videos at 480p or 720p.

Kling 2.5 Turbo
Kling 2.5 Turbo supports text-to-video and image-to-video generation, with smoother motion, more consistent style and realistic physical effects.

Kling 2.1
Kling 2.1 offers realistic motion and high-definition video. Standard provides 720p image-to-video, while Pro and Master provide 1080p output.
Kling Avatar 2.0
Create expressive avatar clips with Kling Avatar 2.0 on Kling 4. Add a portrait, speech or singing audio up to 15 seconds, and a required performance description.

PixVerse V6 Max
PixVerse V6 Max creates cinematic 1–15-second videos from text or an image, up to 1080p, with realistic motion and optional native audio.

OmniHuman 2.0
OmniHuman 2.0 turns one image and 4–300 seconds of audio into a lifelike 720p talking video with natural lip sync, expressions and gestures.

Vidu Q4
Vidu Q4 turns one image or up to 15 references into cinematic 3–16 second videos up to 4K, with native audio and expressive characters.

Gemini Omni 1.1 Flash
Gemini Omni 1.1 Flash extends scenes, links first and last frames and turns prompts, images or a short clip into 4–10 second videos up to 4K.

Wan 3.0 Video Prime
Wan 3.0 Video Prime makes 2–30 second videos with sound at up to 1080p, faster than standard Wan 3.0, from text, keyframes or references.

MiniMax H3
MiniMax H3 (Hailuo 03) makes 4–15 second videos at up to 2K with native stereo sound, from text, keyframes or images and audio.
Tools

Kling 3.0 Motion Control
Use Kling 3.0 Motion Control to transfer movement from a reference video to a character image. Guide body movement and facial expression with 720p or 1080p output.

Kling 2.6 Motion Control
Developed by Kuaishou, Kling AI 2.6 Motion Control is a performance-driven image-to-video model. It precisely transfers real movements, poses and expressions from a reference video to a character image, producing temporally stable, realistic video.
Kling AI Video Models: Frequently Asked Questions
What can I create with Kling?
Kling can be used for AI video generation, image-to-video creation, motion-controlled character videos, native audio-visual output and talking avatar workflows. It suits marketing content, product videos, social media clips, virtual characters and presenter-style videos.
Which Kling model should I choose?
The best choice depends on the output you need. General video generation is better for cinematic scenes, product visuals and short-form content. Motion control is better when a character needs to follow a reference performance. Avatar workflows are better for lip-synced presenters, narration videos and image-plus-audio talking avatars.
Can I test Kling before committing?
Yes. Kling 2.5 Turbo Text and Image need no VIP, so you can run short tests before full production. This helps you compare outputs, adjust prompts, check input quality and understand how different Kling workflows respond.
What inputs does Kling support?
Supported inputs depend on the selected Kling model. Common input types include text prompts, uploaded images, start and end frames, motion reference videos, character images and audio files. Exact input rules, file requirements, duration options and parameters are shown in each workspace.
Does Kling support native audio generation?
Some Kling workflows, such as Kling 3.0, Kling O3 and Kling 2.6, support native audio-visual generation, including speech, dialogue, sound effects, ambient sound and synchronized motion timing. This is useful when sound and visuals need to feel connected from the first output instead of adding audio later.
Is Kling suitable for commercial video projects?
Yes. Kling supports commercial use cases such as product ads, e-commerce videos, creator content, avatar videos and automated media workflows. For specific commercial usage terms and content policy requirements, check our Terms.
Where can I find Kling pricing?
Kling pricing is on our Pricing page, and each workspace shows the credit cost before you submit, so you can estimate cost based on the selected model and actual usage.