Kling 2.6 brings together Pro text-to-video and image-to-video generation with Standard and Pro Motion Control. Create a 5 or 10-second 1080p scene from text or images, and enable native sound when the shot needs dialogue, environmental audio or other prompted sounds. For a prepared first-to-last-frame transition, add the ending image and set sound to false. To transfer a demonstrated action, supply one character image and one motion-reference video; Standard produces 720p and Pro produces 1080p, with duration and cost based on the reference video.
Kling 2.6 is developed by Kuaishou. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Use Pro Text to Video for a written scene and Pro Image to Video for prepared visual material. Select the sound setting and 5 or 10-second duration for those generation tasks. Use Standard or Pro Motion Control when a reference video already demonstrates the action, then prepare the character image, reference clip and orientation that determine the motion workflow.
Transfer reference-video motion onto a character image at 720p with full-body tracking and identity preservation.
Transfer reference-video motion onto a character image at 1080p with high-fidelity tracking for production-ready delivery.
Kling 2.6 Pro Text to Video transforms text prompts into 1080p cinematic videos, featuring native audiovisual synchronization, flexible 5s and 10s durations, and industry-standard aspect ratios. It adheres faithfully to complex scene directions and real-world physical dynamics while preserving spatiotemporal coherence and crisp detail stability.
Kling 2.6 Pro Image to Video animates still images into 1080p cinematic videos, supporting single start-frame generation, optional dual-keyframe control, and native synchronized audio. It injects natural kinetic motion into static visuals while faithfully preserving the original subject identity, clothing textures, and perspective framing.
Text and image generation use the prompt to direct a new scene; image input establishes the subject and composition, and an optional ending frame establishes a destination with sound disabled. Motion Control uses a character image for appearance and a reference video for the demonstrated movement. Choose the task that accepts the material you have prepared, then use its documented fields and current estimate.
| Model / task | Input and workflow |
|---|---|
| Kling 2.6 Standard Motion Control | Transfer reference-video motion onto a character image at 720p with full-body tracking and identity preservation. |
| Kling 2.6 Pro Motion Control | Transfer reference-video motion onto a character image at 1080p with high-fidelity tracking for production-ready delivery. |
| Kling 2.6 Pro Text to Video | Kling 2.6 Pro Text to Video transforms text prompts into 1080p cinematic videos, featuring native audiovisual synchronization, flexible 5s and 10s durations, and industry-standard aspect ratios. It adheres faithfully to complex scene directions and real-world physical dynamics while preserving spatiotemporal coherence and crisp detail stability. |
| Kling 2.6 Pro Image to Video | Kling 2.6 Pro Image to Video animates still images into 1080p cinematic videos, supporting single start-frame generation, optional dual-keyframe control, and native synchronized audio. It injects natural kinetic motion into static visuals while faithfully preserving the original subject identity, clothing textures, and perspective framing. |
Give each source a defined role and describe the action in a clear sequence. The existing records below include spoken scenes from text and images, a mechanical first-to-last-frame transition with sound disabled, and a character driven by a motion-reference video.
Enable sound in the Pro text task and write the scene, spoken words and accompanying sound. The astronaut record asks for a brief line of English dialogue, a floating water droplet and a ventilation hum. Inspect the actual output for the requested voice, expression and scene movement.
Supply the scene image, enable sound and identify the appearance and composition to preserve. The underwater-cabin record asks the researcher to turn slightly, smile and speak while a manta ray glides outside. Compare the image and video for the face, clothing, window and requested dialogue.
Use compatible starting and ending images and describe how the existing parts move. The orrery source supplies the mechanical structure and its intended final arrangement, giving the transition a visible destination to inspect.
Set sound to false when supplying an ending image to Pro Image to Video. Describe the rotation or displacement between the two states, then inspect the completed orrery clip for connected parts, continuous movement and its final relationship to the ending image.
Provide one character image and one reference video for Motion Control. Choose image or video orientation, prepare a reference clip within its corresponding duration range and select Standard 720p or Pro 1080p. The tai chi record shows the prepared woman following a reference routine in a misty park.
The first record supplies an underwater-cabin image and asks the researcher to say “We have company.” while retaining her face, clothing and surroundings. Sound is enabled for that 5-second scene. The second supplies a character image and tai chi reference video, using Standard Motion Control with image orientation. Read the full prompts, inspect every source and compare each actual video with the movement and appearance requested for that record.
Animate this exact underwater observation cabin in one continuous five-second shot. Preserve the researcher's identity, orange shirt, cabin and round window. She turns her face slightly toward the camera, smiles with quiet surprise and says clearly in English, 'We have company.' Natural synchronized lips, eyes and subtle expression; finish the sentence by the fourth second. Outside the window, the single manta ray continues gliding forward toward the right edge of the window, gently moving its broad fins. Faint moving blue caustics play on the cabin wall. Fixed camera, believable human movement and stable facial features. Native audio: her warm close voice, low enclosed cabin ventilation and a distant muted watery rumble. No music, subtitles, text, added characters or cuts.
The silver-haired senior woman in the flowing white tai chi uniform performs the slow, continuous tai chi routine from the reference video in a quiet misty park, keeping her face, hairstyle and identity perfectly consistent, soft morning light, green trees in the background
Prepare a scene brief for text generation, an existing image for animation, two visual states for a transition, or a character image and video for motion transfer. Match those inputs to the task, describe the action and sound where supported, then inspect the completed video for a narrative concept, character presentation, explanatory animation or application workflow.
Write a character, setting, short spoken line and environmental sounds, then enable sound in Pro Text to Video. Review voice, expression and the timing of the action for a scene proposal.
Prepare an image with a clearly visible face and describe the speech, expression and small body movement. Enable sound, generate the shot and inspect appearance and dialogue for a character presentation.
Prepare compatible first and last images, describe how connected parts move and set sound to false. Compare the completed transition with the intended structure and final position for an explanatory animation.
Provide one character image and a reference clip that clearly demonstrates the action. Choose the orientation and Standard or Pro tier, then inspect identity, limb movement and continuity for a motion study.
Use a 3–10-second reference for image orientation or a 3–30-second reference for video orientation. Review the detected duration and current rate when planning the complete motion-transfer request and its budget.
Retain the selected model, prompt, media URLs and task-specific sound, duration or orientation settings. Submit the authenticated API request and track its task ID to obtain the generated video.
Pro text and image generation are billed per video, with separate rates for 5 and 10 seconds and for the sound setting. Standard and Pro Motion Control are billed per second using the detected reference-video duration; the credit calculation uses that duration and rounds the resulting credits upward. The dynamic table shows the current starting rate and billing unit for each task. Open the selected task to review its full estimate with your actual settings and reference clip.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Kling 2.6 Standard Motion Control | Kling | Motion Control | Character image + motion video | 720p | $0.04 / second |
| Kling 2.6 Pro Motion Control | Kling | Motion Control | Character image + motion video | 1080p | $0.06 / second |
| Kling 2.6 Pro Text to Video | Kling | Text to Video | Text prompt | 5 / 10 s · 1080p | $0.325 / video |
| Kling 2.6 Pro Image to Video | Kling | Image to Video | Image frames / optional ending frame | 5 / 10 s · 1080p | $0.325 / video |
Test your creative brief online, then bring the verified request into your application.
Open the matching task and supply its required text and media. For scene generation, choose 5 or 10 seconds and the sound setting. For Motion Control, upload the character image and reference video, choose image or video orientation and review the detected duration. Check the estimate, generate the video and inspect action, appearance and any requested sound.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Pro Text to Video for a written scene or Pro Image to Video for an existing image and optional ending frame. Set sound and a 5 or 10-second duration; set sound to false when using an ending frame. For a demonstrated action, choose Standard 720p or Pro 1080p Motion Control and prepare one character image, one reference video and the orientation setting.
Open the matching task, enter your brief and supply the required images. Review the generated result against subject appearance, composition and the requested changes before carrying the workflow into a project.
Review the selected video duration and sound tier for Pro generation. For Motion Control, review the reference clip’s detected duration and the Standard or Pro per-second rate. Use the complete estimate and planned test count to budget your workflow.
Read the actual prompt and inspect its source images and result together. Use those examples to understand how to assign input roles and describe the details to preserve or change in your own request.
Retain the task ID returned by the API to query status and retrieve completed file URLs. Use your online generation history to review earlier results and the creative direction you tested.
Use the documentation linked from each task for its exact model identifier, accepted inputs, authentication and response format. Integrate the same task you tested online so its media and settings match the request.
Kling 2.6 is a Kuaishou video family available through four Vidgo tasks: Pro Text to Video, Pro Image to Video, Standard Motion Control and Pro Motion Control. The first two create 5 or 10-second 1080p videos with a sound setting. Motion Control transfers a reference video’s action to one character image at Standard 720p or Pro 1080p.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
