Kling 4.0 is now in Picsart with 30-second and 4K video generation

Kling 4.0 is now available in Picsart, and it turns a single generation into up to 30 seconds of continuous video in up to 4K. Open it in AI Playground to place up to 10 keyframes along the timeline, or switch to Kling 4.0 Omni to combine as many as 15 references and edit footage you already have with a written instruction. Two models arrive together: Kling 4.0 and the reference-driven Kling 4.0 Omni.

What is Kling 4.0?

Kling 4.0 is the newest video model in the Kling family, built to generate video from a text prompt or an image, while Kling 4.0 Omni handles references and video editing. Kling describes it as a native multimodal model, and the upgrade centres on three things: longer single takes, steadier motion, and tighter control over how a story unfolds.

The motion gains show up in the hardest scenes to fake. Fast fights, competitive sports, large-scale action and complex camera work such as tracking shots and orbits hold their structure, so limbs, spatial relationships and camera rhythm stay connected even as the action speeds up. Faces, materials and lighting look more natural, and small shifts in expression carry real emotional weight.

Prompts can now run up to 8,000 tokens, which leaves room to script action, dialogue, camera moves and sound in detail. A one-line idea works too. Kling 4.0 expands a simple prompt into a fuller scene, filling in story beats, blocking and camera movement.

Kling 4.0 and Kling 4.0 Omni

Kling 4.0 is the one to reach for when a shot starts from a prompt or a single image and needs a long take or precise direction. Kling 4.0 Omni works from a stack of references instead, which makes it the pick for consistent characters, product swaps and edits to existing footage. The wider Kling 4.0 lineup also includes Kling 4.0 Flash, a faster, lighter version built for quick drafts and high-volume work. It handles text-to-video, image-to-video and reference-based generation in clips of 3 to 20 seconds at 720p, trading length and resolution for faster turnaround at a lower cost.

30-second videos with keyframe control

Kling 4.0 generates anywhere from 3 to 30 seconds natively, in a single pass. That is enough time to establish a place, introduce a character, build the action and land a clear ending without stitching clips together. Multi-shot is on by default, so the model splits a long generation into shots and paces them to fit the content.

Longer clips raise a new question: does each moment happen when it should? Multiple Keyframes answer it. Place up to 10 keyframe images along the timeline to fix character poses, scene changes, product reveals and shot transitions, then let the prompt describe the action and camera movement in between. First and last frame control is still there for simpler start-to-finish moves.

Camera direction gets the same upgrade. Push-ins, pull-outs, pans, tracking shots and orbits feel more natural, and changes in shot size flow smoothly from one beat to the next. Frame it all in 21:9, 16:9, 1:1 or 9:16, or leave the aspect ratio on Auto. Output comes in 720p, 1080p or 4K, and 4K is the pick for large-screen playback, commercial campaigns and footage headed for further editing.

Direct with references, edit with prompts

Omni Reference in Kling 4.0 Omni lets images, videos and subjects work together in the same generation, so each asset can carry one part of the brief instead of a prompt trying to describe everything.

Up to 15 references in one generation

A single Kling 4.0 Omni generation accepts up to 15 reference assets in total, within these limits:

• Up to 10 images, such as character turnarounds, image grids, storyboards, wireframes and product shots
• Up to 5 videos with a combined length of 30 seconds, including white-model and depth-map videos for precise motion and timing
• Up to 7 subjects, including up to 3 built from video
• Up to 3 voice profiles that give a character a consistent vocal identity

The trick is giving every reference a clear job. One image sets the face and outfit, another sets the room, and a video sets the fight choreography or the camera path. The same woman can then move from a table-side shot to a bedroom to an overhead view and stay recognizably herself.

Recreate a video you like

Kling 4.0 Omni can borrow the pacing, shot composition and camera movement of an existing video while swapping in your own characters, products and settings. Take the structure of a trending product ad, drop in a different product, and adapt the cast and scene to fit a brand. Clips closer in pacing and shot structure to the target content recreate most faithfully.

Edit footage you already have

Targeted editing in Kling 4.0 Omni changes one thing and leaves the rest of the scene alone. Adjust a character’s expression or movement, move the camera, restyle the whole clip, swap the background, add a new element, replace a cast of characters or remove a person from the foreground. An editing task takes up to 5 video clips, including 1 primary video, with each clip 3 to 30 seconds long and 30 seconds combined. Pairing an edit with reference images gives the best results.

Sound, speech and on-screen text

Kling 4.0 generates two-channel stereo audio with sharper lip sync, so dialogue, mouth movement and performance stay aligned and ambient sound gains a real sense of space. Speech covers Chinese, English, Japanese, Korean, Spanish, Portuguese, German, French, Hindi and more. Accents and dialects include Beijing, Taiwanese, Northeastern Chinese, Sichuanese and Cantonese, plus American, British and Indian English.

On-screen text gets the same care. Multilingual text, logos and emojis stay legible and stable while the camera moves and scenes change, so product names, slogans and title cards read cleanly throughout.

What you can make with Kling 4.0

Brand ads and product videos. Keep a product’s shape, colors and logo consistent across changing angles and lighting with Kling 4.0 Omni, or use the full 30 seconds of Kling 4.0 to move from an opening scene to a close-up, product in use and a final hero shot.

Short films and short dramas. Long generation, character performance and keyframe control come together for scenes with a beginning, middle and end, in styles from realistic documentary to vlog to cinematic.

UGC and social content. Reviews, unboxings and creator-style ads benefit from natural performances and dialogue, and recreation in Kling 4.0 Omni makes it quick to adapt a format that already works on social.

Animation and music videos. Claymation, felt textures, pixel art, glitch art and 3D cyberpunk worlds are all in range, and video references in Kling 4.0 Omni can guide dance moves, camera direction and timing.

Pre-production. Turn a storyboard or a set of visual references into a concept video with Kling 4.0 Omni or scene preview before committing to a full shoot.

What’s new in Kling 4.0

Kling marks these upgrades as new in this Kling 4 generation, which picks up where Kling 3.0 left off:

• Native generation from 3 up to 30 seconds
• Multiple Keyframes, with up to 10 keyframe images per video
• 21:9 ultrawide framing alongside 16:9, 1:1 and 9:16
• Two-channel stereo audio
• Prompts of up to 8,000 tokens
• German, French and Hindi speech, plus clearer multilingual text, emojis and logos

Start creating with Kling 4.0

Kling 4.0 brings 30-second storytelling and keyframe timing, and Kling 4.0 Omni adds reference-driven editing. Open AI Playground, choose Kling 4.0 or Kling 4.0 Omni, and give your next idea the full half minute it deserves.