Animate a photo with Grok Imagine Video 1.5 by xAI at up to 1080p, or switch to the other Grok version to make a clip from text alone.
Model
Grok Imagine Video 1.5 by xAI animates a start photo you upload, at up to 1080p and 1 to 15 seconds, in your photo's shape. The other version also works from text alone, with sound and seven shapes.
Upload a photo, describe the motion, and Grok Imagine turns it into a short clip.
Image to video
Grok Imagine Video 1.5 on Pixelcut needs a start photo, and every clip opens on the frame you picked. Upload it, write one line about what moves and how the camera travels, and generate. Starting from words instead? The other Grok version takes a prompt alone.
Version 1.5 starts every clip from a photo you upload, and the first frame is yours. Your prompt only has to say what changes. The colors and setting already come from your picture, and the motion picks up right where it stands.
Get version 1.5 clips at up to 1080p on Pixelcut. Choose full HD for close ups and any clip headed for a large screen. Detail shots get the extra resolution they need.
No photo to start from? The other Grok version on Pixelcut makes the whole clip from a line or two of text. It also creates a sound track with the picture. You get a finished scene with sound, ready to share.
Make clips anywhere from 1 to 15 seconds long on either version. Cut a quick hook or let a scene play out across the full 15. Version 1.5 keeps the shape of your photo, and the other version offers seven shapes from wide to tall.
Online sellers, social creators and concept artists use Grok Imagine on Pixelcut to turn stills and ideas into clips.
Turn a product photo into an ad that moves. Use it on your listings and paid posts to catch shoppers mid scroll, with no video shoot to plan.
Turn your best photo into a clip your followers stop to watch, ready to post the same day. Explore the AI video generator for more looks.
Give a character design its first move. Upload your concept art and watch it come alive, ready to pitch to your team or share with fans.
Switch models per generation instead of per subscription. Each card opens that model's page.
Cinematic motion, and your first video is free
ByteDance's newest video model
Text, image and reference video, up to 15 s
Photoreal video with synchronized audio
Multi-shot scenes and elements
Synchronized audio in many languages
Version 1.5 needs one photo to begin. Choose a portrait, a product shot, a pet or a piece of concept art. Its shape becomes the shape of the finished clip.
Write what moves, how the camera travels and where the light falls, such as a slow push in on a sleeping cat as morning sun creeps across its fur.
Stay on 1.5 for up to 1080p, or switch to Grok Imagine Video for text alone, seven shapes and sound. Then set a length anywhere from 1 to 15 seconds.
Each clip takes about a minute, going by the model picker's estimate. Play it back, save the MP4, or change a few words in your prompt and run another take.
Video is billed in credits per second of footage. Pick the plan that matches how much you make.
Trusted by creatives at
