Grok Imagine 1.5
Grok Imagine 1.5 is a video generation model from X.ai that accepts text, image, and video inputs to produce generated video output.
Text and image-to-video generation from X.ai
Grok Imagine 1.5 is a video generation model developed by X.ai, the AI division associated with the Grok family of models. It accepts source images, source videos, text prompts, aspect ratio settings, and duration parameters as inputs, enabling both image-to-video and video-to-video generation workflows. The model carries a context window of 131,072 tokens and is available as a first-party offering on supported platforms.
Grok Imagine 1.5 is priced between $0.08 and $0.25 per second of generated video, reflecting variable costs based on output length or quality settings. It is suited for tasks such as animating still images, extending or transforming existing video clips, and generating short video content from descriptive prompts. The model supports selectable aspect ratios and configurable duration, giving developers control over the format of the output video.
What Grok Imagine 1.5 supports
Image-to-Video
Animates a source image into a video clip. Accepts an image URL as input and produces a generated video based on the provided image and prompt.
Video-to-Video
Transforms or extends an existing video clip using a source video URL input. Enables style transfer, continuation, or modification of existing footage.
Aspect Ratio Control
Allows selection of output video aspect ratio via a configurable select input. Supports different framing options to match target display formats.
Duration Control
Accepts a numeric duration parameter to specify the length of the generated video output. Pricing scales with duration at $0.08–$0.25 per second.
Large Context Window
Supports a context window of 131,072 tokens, allowing detailed and lengthy text prompts to guide video generation.
Ready to build with Grok Imagine 1.5?
Get Started FreeCommon questions about Grok Imagine 1.5
How is Grok Imagine 1.5 priced?
Grok Imagine 1.5 is priced between $0.08 and $0.25 per second of generated video. The variable rate likely reflects differences in output resolution, quality settings, or duration.
What input types does Grok Imagine 1.5 accept?
The model accepts a source image URL, a source video URL, an aspect ratio selection, and a numeric duration value. This allows image-to-video, video-to-video, and text-guided generation workflows.
What is the context window for Grok Imagine 1.5?
Grok Imagine 1.5 has a context window of 131,072 tokens, which can be used to provide detailed text prompts alongside image or video inputs.
Who publishes Grok Imagine 1.5?
Grok Imagine 1.5 is published by X.ai and is available as a first-party model, meaning it is served directly by the model's creator.
Can I control the length and format of the generated video?
Yes. The model includes inputs for both aspect ratio (via a select field) and duration (via a numeric field), giving you control over the shape and length of the output video.
Documentation & links
Parameters & options
Explore similar models
Start building with Grok Imagine 1.5
No API keys required. Create AI-powered workflows with Grok Imagine 1.5 in minutes — free.