Grok Imagine Video creates 6- or 10-second clips from text or one prepared image. Use Text to Video to describe the subject, setting, action and camera and choose a square, portrait or landscape aspect ratio. Use Image to Video to animate an existing person, animal or object while describing the movement and appearance to preserve. Select the documented generation mode and duration, then review the per-video estimate for a storyboard, character moment, miniature animation or moving scene.
Grok Imagine Video is developed by xAI. Vidgo provides access to the model. Model names and trademarks belong to their respective owners.Choose Text to Video when the scene begins with words. Choose Image to Video when the subject and composition are already prepared in an image. Describe the action in order, identify the camera behavior and details to preserve, and select a 6 or 10-second duration with the generation mode suited to your test.
Create 6- or 10-second clips with Grok Imagine Video Text to Video. Describe scenes and motion, then choose a generation mode and video aspect ratio.
Animate a still image with Grok Imagine Video Image to Video. Add a motion prompt, choose a generation mode, and create a 6- or 10-second video clip.
The text task describes the whole scene and accepts an aspect-ratio setting. The image task accepts exactly one image_urls entry and uses its visual content to guide the animation. Both tasks accept a motion prompt, a generation mode and a 6 or 10-second duration. Choose the input method around the material you have prepared and the result you want to inspect.
| Model / task | Input and workflow |
|---|---|
| Grok Imagine Video Text to Video | Create 6- or 10-second clips with Grok Imagine Video Text to Video. Describe scenes and motion, then choose a generation mode and video aspect ratio. |
| Grok Imagine Video Image to Video | Animate a still image with Grok Imagine Video Image to Video. Add a motion prompt, choose a generation mode, and create a 6- or 10-second video clip. |
Write a concrete sequence and explain how the subject interacts with the scene. The existing records below include a cardboard robot passing a gate, an acrobat’s baton action, a portrait animation and a ceramic crab moving through a handcrafted setting.
Describe the subject’s shape, the obstacle and the ordered action. The cardboard-robot record uses fun mode for a 6-second scene in which the robot turns sideways to pass an open ticket gate. Inspect the rigid cardboard form and movement against the prompt.
Use 10 seconds when your brief needs several connected actions. The acrobat record describes a single baton toss and catch followed by a half turn and bow, keeping the full body and object visible. Review how the generated clip follows that sequence.
Supply the photograph and identify the face, hair, clothing, background and framing to preserve. The photo-booth input establishes the man and his crooked bow tie before the prompt directs hand movement and a restrained expression.
Describe the action order and the final expression. The photo-booth record asks the man to straighten his bow tie once, lower his hands and finish with a small grin. Compare the source and actual video for appearance, hand motion and the fixed framing.
Use the image and prompt to identify rigid parts, joints and surface texture. The ceramic-crab record requests two sideways steps and a claw salute while keeping the cobalt glaze, legs and winding key. Inspect the generated movement against those material and structural instructions.
The first record supplies a photo-booth portrait and requests a 10-second sequence of straightening a bow tie and suppressing a smile in normal mode. The second supplies the ceramic crab and requests two steps and a salute over 6 seconds in fun mode. Read the complete prompts and compare each image with its corresponding actual video to inspect the requested action, appearance and material continuity.
Animate this exact photograph as one continuous ten-second fixed medium close-up. The same curly-haired middle-aged man in the photo booth glances down at his crooked bow tie, uses his hands to gently straighten it once, lowers his hands, then looks directly into the camera and tries to suppress a smile, ending with a small warm grin. Preserve his exact face, hair, jacket, shirt, booth curtain, framing and photographic lighting. Natural small hand movements and subtle cheeks and eyes; no talking, no exaggerated laughter, no camera movement, no cuts, no new objects or text.
Bring the same small blue ceramic clockwork crab to life in a six-second handcrafted stop-motion animation. It takes exactly two small sideways steps across the checkerboard table, pauses, then raises one claw in a cheerful little salute. Keep the same number of legs and claws, the same glossy cobalt glaze with tiny handmade imperfections, and the same visible brass winding key. Body remains rigid ceramic, legs rotate at their joints. Fixed camera, steady warm kitchen light, no extra objects, no cuts, no morphing, no text or logos.
Prepare a written scene for a new character or location, or one image for an existing portrait, animal or object. Describe the action, camera and details to preserve, select 6 or 10 seconds and the generation mode, then inspect the video for a storyboard, character presentation, wildlife study, miniature animation or integrated creative workflow.
Write the character’s material, setting and one clear interaction. Choose a mode and duration, then inspect the action and scene structure for a storyboard concept.
Describe the person, visible object and ordered movement, and choose a duration suited to the sequence. Review body continuity and object handling for a performance or character proposal.
Provide one portrait and describe a restrained gesture and expression. Identify the face, clothes and background to preserve, then compare the completed video with the image for a character presentation.
Supply a clear animal image and describe a small action, breathing or local environmental change. Inspect anatomy and source composition for a natural-history visual study.
Prepare the object image and specify its rigid body, moving joints and intended action. Review surface texture and structural continuity before selecting the clip for a miniature presentation.
Retain the task identifier, prompt, optional source-image URL, mode and duration. Submit the authenticated request and track its task ID to retrieve the completed video.
Grok Imagine Video is billed per video using the selected 6 or 10-second duration tier. The dynamic table shows the current lowest per-video price for each task. Open the text or image task, select the intended duration and mode and review the complete estimate for that clip before generating.
| Model | Provider | Workflow | Input material | Output specification | Starting rate |
|---|---|---|---|---|---|
| Grok Imagine Video Text to Video | xAI | Text to Video | Text prompt | 6 / 10 s | $0.15 / video |
| Grok Imagine Video Image to Video | xAI | Image to Video | One source image | 6 / 10 s | $0.15 / video |
Test your creative brief online, then bring the verified request into your application.
Enter the scene or motion prompt, provide one source image for image generation and select the mode and 6 or 10-second duration. Configure the text task’s aspect ratio where needed. Review the estimate, generate the clip and inspect movement, subject appearance, materials and framing.
Choose a task, inspect its settings and cost, and follow the result from an online test to an authenticated API request.
Choose Text to Video for a written scene or Image to Video for one prepared image. Describe the ordered action and camera, choose a documented mode and select 6 or 10 seconds. Set the aspect ratio in the text task when preparing a square, portrait or landscape composition.
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.
Select the intended duration to review the full per-video price. Use the complete estimate and planned test count when budgeting a scene or animation study.
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.
Grok Imagine Video is an xAI video model available on Vidgo through Text to Video and Image to Video. It creates 6- or 10-second clips from a written scene or one source image, with documented mode choices and aspect-ratio controls for the text task.
Explore model introductions, API guides and platform comparisons to understand input preparation, request integration and cost planning for your project.
