Kling O1
The world's first unified multimodal video model. Accept text, image, and video inputs simultaneously. Combine up to 7 reference elements (characters, avatars, props, outfits, scenes) for unmatched consistency and creative control.
Try Kling O1 NowCreate Videos in 3 simple steps
Tell your vision
Write a prompt describing your video. Kling O1 accepts text, image, and video inputs simultaneously for maximum creative control.
Add references
Upload up to 7 reference elements: characters, avatars, props, outfits, and scenes. Use video as motion reference to copy actions or camera movements, or as the base for transformations.
Edit or share
Preview your video with perfect visual consistency across all elements, make adjustments if needed, and download or share your creation directly from Freepik.
Complex editing workflows
Build advanced production pipelines combining multiple references and modifying existing videos with precision.
Storyboarding with existing assets
Use your own characters, scenarios, and elements to create animated storyboards while maintaining total visual consistency.
Video re-styling
Transform existing videos: change visual styles, modify backgrounds, and add or remove elements. Adjust shot sizes and camera movements while preserving the original motion.
What our creators are saying
Rachel Kim
Motion Designer, Pixel Perfect Studio
Kling O1 understands exactly what I want to achieve. The ability to combine 7 different references in one generation has revolutionized how we create content for brands.
David Okonkwo
Marketing Lead, FutureTech Startups
Being able to edit existing videos with text prompts is incredible. We repurpose old content giving it a completely new look without re-shooting anything.
Laura Vega
Brand Strategist, Creativa Digital
It's truly 'the video Nano Banana'. The consistency between characters and scenes we achieve now was impossible with other models. A game changer for our clients.
Create AI videos with Kling O1, now on Freepik
Discover the world's first unified multimodal video model. Generate, edit, and transform videos with complete creative control using advanced AI technology, now available on Freepik.
Create with Kling O1Tools to skyrocket your creative freedom
More tools and features coming soon! Want to test them before anyone? Become our AI partner.
Explore other AI models
Discover our collection of AI-powered generation tools
Frequently Asked Questions
- Kling O1 STD (720p) costs 75 cr/sec without video reference and 110 cr/sec with video reference. Kling O1 PRO (1080p) costs 100 cr/sec without video reference and 150 cr/sec with video reference.
- Kling O1 is the first model that accepts text, image, and video inputs simultaneously. You can combine up to 7 reference elements (characters, avatars, props, outfits, scenes) without video, or up to 4 references when including a video reference.
- Yes, you can upload a 3-10 second video and modify elements, backgrounds, or styles using text prompts. Kling O1 renders at 60fps for exceptionally smooth results. This allows you to transform existing content without starting from scratch.
- Kling O1 is nicknamed "The Video Nano Banana" because it solves the consistency problem in video generation—similar to how Nano Banana revolutionized image consistency. It maintains perfect visual coherence across characters and scenes.
- Yes, you can use any video to copy actions or camera movements into a completely new scene. This transfers movement dynamics seamlessly while creating entirely new visuals.
If you need further information, please contact us