Skip to main content
AI video model
xAI
Grok Imagine

Grok Imagine Video 1.5 Preview

Does Kyeo AI currently use Grok Imagine Video 1.5 Preview? Platform route selection — 1–15 seconds; 480p or 720p; up to 7 reference images

Current input
Text or up to 7 reference images
Base generation
Base generation — 480p 2.4 or 720p 4.5 credits/second
Duration
1–15 whole seconds; default 8 seconds
Resolution
480p / 720p
30-second overview
  • Unified input — Start from a text prompt or a set of reference images without changing tools.
  • Duration — 1–15 seconds; 480p or 720p; up to 7 reference images
  • Grok Imagine — The selected resolution rate is multiplied by 1–15 seconds and rounded up: 480p costs 3–36 and 720p 5–68 credits, for an overall 3–68 range.
  • Aspect ratio — 480p/720p accept up to 7 JPEG, PNG, or WebP reference images at 20MB each.
  • result actions — Legacy Extend and Upscale result actions are outside the current 1.5 Preview contract, so the UI hides them and the server rejects them.

Popular searches: Does Kyeo AI currently use Grok Imagine Video 1.5 Preview? Platform route selection · How is Grok Imagine Video 1.5 Preview billed? Base pricing · What happens to aspect ratio after I upload images? Image input

Examples

Fashion portrait

Fantasy scene

Fantasy scene

Cinematic scene

Duration: 15s | 16:9 Landscape | Native 4K UHD | 24fps Genre: Cinematic Slice-of-Life Fantasy Comedy Target: Ultra-realistic premium live-action fantasy cinema REFERENCE LOCK — @<image1 Use @<image1 as the sole identity reference. Preserve Character A exactly as shown. Exactly one Character A. No redesign, duplication, morphing, identity drift, outfit change, or hairstyle change. CORE CONCEPT Inside an old witch’s cozy kitchen, Character A tries to pour tea from an enchanted silver teapot. The teapot is sitting too far away on a wooden counter. Character A uses one wand to magically pull it closer, but the spell is far too strong. The teapot rockets across the kitchen, flies directly toward Character A, then stops inches before impact and gently pours tea into a cup by itself. SHOT 1 — 0s–4s | THE PROBLEM Wide cinematic kitchen shot. Character A reaches toward a silver teapot positioned far across the wooden counter. The hand clearly cannot reach it. Character A tries once, fails, then gives a tired annoyed look toward the teapot. Slow push-in. Warm morning light through dusty windows. Steam from an old kettle. Natural fabric movement and realistic hand anatomy. SHOT 2 — 4s–7s | THE SPELL Medium profile shot. Character A slowly raises one wand. Extreme close-up of wand tip. Silver-blue magic activates with a restrained glow. Cut to an aligned side angle showing: WAND → OPEN KITCHEN SPACE → TEAPOT At 6s, a thin blue-white magical tether directly connects to the teapot handle. Contact spark. The teapot immediately begins moving. SHOT 3 — 7s–11s | TOO MUCH POWER The teapot suddenly launches across the counter with realistic inertia. Low tracking camera follows it. Tea inside visibly sloshes naturally. Character A's eyes widen slightly but expression remains restrained. At 9.5s, teapot rapidly enters foreground. Character A instinctively leans back. At 10s, teapot stops suddenly just inches from Character A's face. No collision. A brief silence. SHOT 4 — 11s–15s | PERFECTLY USELESS MAGIC Character A slowly looks at the floating teapot. The teapot gently rotates itself. Tea pours perfectly into a waiting cup. Character A watches silently. One tiny exhausted blink. Character A takes the cup and walks away. End while moving. No smile, no camera look, no victory pose. AUDIO + MUSIC Cozy room ambience, wood creaks, ceramic movement, wand ignition, magical hum, rushing air, tea sloshing, pouring tea and footsteps. Music: acoustic guitar, muted piano, soft pizzicato strings, playful clarinet and brushed percussion. Music remains below SFX. No dialogue, vocals, boing, circus music, laugh track or meme sounds. CAUSALITY TEAPOT TOO FAR → HAND FAILS → WAND RAISES → MAGIC CONNECTS → TEAPOT LAUNCHES → RAPID APPROACH → SUDDEN STOP → TEA POURS → CHARACTER A LEAVES. NEGATIVE PROMPT Extra characters, duplicate teapot, duplicate wand, floating objects before activation, teleportation, broken physics, cartoon animation, exaggerated facial expressions, plastic skin, cheap CGI, malformed hands, identity drift, outfit change, face morphing, subtitles, text, logo, watermark.

Fantasy scene

Fashion portrait

At a glance

Is this model right for you?

Before submission, the workbench calculates integer credits from resolution and duration and validates image count, single-image ratio behavior, and the safety setting.

What it does best
This is the current Grok Imagine Video 1.5 Preview generation page, not a compatibility layer for the legacy Grok Imagine routes.
Who it is for
Best for short-video openings, product visuals, character motion, concept shots, and social assets that benefit from native audio.
Why use it on Kyeo AI
One workbench combines text and multi-image input, duration, resolution, safety checking, and a live cost estimate.

Key facts

Quickly evaluate whether this model fits your business use case.

Model vendor
xAI
Integration
Current site integration
Model version
1.5 Preview
Current input
Text or up to 7 reference images
Duration
1–15 whole seconds; default 8 seconds
Resolution
480p / 720p
Prompt language
The current 1.5 Preview workflow can generate native audio with the video.

Other names

The same model may have different names in official documentation, community discussions, and API integrations. This section brings them together for you.

Grok Imagine Video current version
Grok Imagine Video 1.5 Preview
xAI Grok Imagine Video 1.5

Common questions

These practical questions focus on the task, input conditions, and result requirements you should confirm before choosing.

Does Kyeo AI currently use Grok Imagine Video 1.5 Preview? Platform route selection
How is Grok Imagine Video 1.5 Preview billed? Base pricing
What happens to aspect ratio after I upload images? Image input
Does it generate native audio? Generation modes
Can I still use the legacy Extend or Upscale actions? Result actions
Does Kyeo AI currently use Grok Imagine Video 1.5 Preview? Video duration
How is Grok Imagine Video 1.5 Preview billed? Resolution
What happens to aspect ratio after I upload images? Aspect ratio
Does it create native audio, and can safety screening be adjusted?
Can I still use the legacy Extend or Upscale actions? Video duration

Decision guide

Still deciding? Start with these key decision points.

1
Choose text or image input

Choose text or image input — 480p/720p accept up to 7 JPEG, PNG, or WebP reference images at 20MB each.

2
Choose 480p or 720p

Choose 480p or 720p — The selected resolution rate is multiplied by 1–15 seconds and rounded up: 480p costs 3–36 and 720p 5–68 credits, for an overall 3–68 range.

3
Confirm the input setup before submitting

Confirm the input setup before submitting — 1–15 seconds; 480p or 720p; up to 7 reference images

Popular comparisons

Compare common alternatives on the same task to clarify differences in inputs, controls, and cost.

Platform route selection: Grok Imagine Video 1.5 Preview
Base pricing: Grok Imagine Video 1.5 Preview / Kling 3.0
Image input: Grok Imagine Video 1.5 Preview / Kling 3.0
Result actions: Does it generate native audio?
Should I use Grok Imagine Video with text or an image?
Base pricing — 480p / 720p

Model comparison table

Not sure which model to choose? Compare the key differences between this model and its alternatives at a glance.

Platform route selection
Grok Imagine Video 1.5 Preview
The current 1.5 Preview workflow supports both text prompts and reference-image input in one experience.
Kling 3.0
Platform route selection — Kling 3.0: A currently available alternative in the same category; open its detail page to compare capabilities and pricing.
Veo3.1 Fast
Veo 3.1 route with first/last-frame and reference-image modes
Base pricing
Grok Imagine Video 1.5 Preview
Base pricing — The selected resolution rate is multiplied by 1–15 seconds and rounded up: 480p costs 3–36 and 720p 5–68 credits, for an overall 3–68 range.
Kling 3.0
Base pricing — Kling 3.0: A currently available alternative in the same category; open its detail page to compare capabilities and pricing.
Veo3.1 Fast
Current credit settings
Image input
Grok Imagine Video 1.5 Preview
480p/720p accept up to 7 JPEG, PNG, or WebP reference images at 20MB each. — Aspect ratio — With exactly 1 image, the source ratio is preserved and `aspect_ratio` is omitted.
Kling 3.0
Image input — Kling 3.0: A currently available alternative in the same category; open its detail page to compare capabilities and pricing.
Veo3.1 Fast
First/last-frame or reference-image modes
Safety screening
Grok Imagine Video 1.5 Preview
On by default and can be turned on or off before submission.
Kling 3.0
Generation modes — Kling 3.0: A currently available alternative in the same category; open its detail page to compare capabilities and pricing.
Veo3.1 Fast
Output, sound, and shot controls
Result actions
Grok Imagine Video 1.5 Preview
Legacy Extend and Upscale result actions are outside the current 1.5 Preview contract, so the UI hides them and the server rejects them.
Kling 3.0
Result actions — Kling 3.0: A currently available alternative in the same category; open its detail page to compare capabilities and pricing.

Real-world experience

Practical guidance based on public sources, current on-site limits, and representative tasks.

The current version unifies text and image creation

The workbench keeps text prompts and reference-image input in one clearly labelled workflow.

Reference-image count and formats

At 480p or 720p, upload up to 7 JPEG, PNG, or WebP reference images, each no larger than 20MB.

Capabilities

Text-to-video

Text-to-video — 1–15 seconds; 480p or 720p; up to 7 reference images

Multiple reference images

At 480p or 720p, upload up to 7 JPEG, PNG, or WebP reference images at 20MB each. With exactly 1 image, its original aspect ratio is preserved automatically.

Safety screening and result actions

Safety screening is on by default and can be disabled before submission. The current 1.5 Preview does not offer the legacy Extend or Upscale result actions.

Use cases

Text-defined concept shot

Describe the subject, action, camera movement, environment, and pacing for one video segment.

Animate a key visual

Animate a key visual: One-image video: Upload up to 7 reference images. With exactly 1 image, the source ratio is preserved and `aspect_ratio` is omitted.

Landscape and portrait assets

Choose 16:9 or 9:16 for text-to-video. Prepare the source image at the target ratio for image-to-video.

Prompt tips

Grok Imagine Video 1.5 Preview prompt

Grok Imagine Video 1.5 Preview prompt: Describe the subject, action, camera, environment, and sound clearly; with multiple images, state the role of each reference.

Separate action from camera direction

Separate action from camera direction: Describe the subject, action, camera, environment, and sound clearly; with multiple images, state the role of each reference. The current 1.5 Preview workflow can generate native audio with the video.

Download completed results promptly

The public source interface's general task documentation says generated links typically expire after about 24 hours.

Why choose it

Current version — One workflow handles text prompts and reference-image input.
Current version — One workflow handles text prompts and reference-image input. — 1–15 seconds; 480p or 720p; up to 7 reference images
Text or up to 7 reference images; Up to 7 JPEG, PNG, or WebP images, each no larger than 20MB
The current 1.5 Preview workflow can create native audio with the video, and safety screening is on by default but adjustable.

What to know first

Generate one representative sample with the selected parameters and confirm that it meets the goal before scaling up.
Generate one representative sample with the selected parameters and confirm that it meets the goal before scaling up. — 480p/720p accept up to 7 JPEG, PNG, or WebP reference images at 20MB each.
Aspect ratio — With exactly 1 image, the source ratio is preserved and `aspect_ratio` is omitted.
Safety screening is on by default; if you disable it, review media rights, intended use, and the output yourself.
Server guard — Legacy Extend and Upscale result actions are outside the current 1.5 Preview contract, so the UI hides them and the server rejects them.

Adjustable settings

Quickly evaluate whether this model fits your business use case.

Video duration
Optional
Parameter type: number
8
Range — 1–15 whole seconds; default 8 seconds
Resolution
Optional
Parameter type: select
480p
480p
720p
Aspect ratio
Optional
Parameter type: select
auto
auto
1:1
16:9
9:16
3:2
2:3
Safety screening
Optional
Parameter type: select
true
true
false

Credit cost

480p 2.4 or 720p 4.5 credits/second

The selected resolution rate is multiplied by 1–15 seconds and rounded up: 480p costs 3–36 and 720p 5–68 credits, for an overall 3–68 range.

Credit-saving tip

Before generating images or videos in bulk, run an A/B test with the same input on this model and similar alternatives. Confirm the result first to avoid wasting credits.

Frequently asked questions

Related models

Still deciding? Take a quick look at these similar alternatives.

Kling 3.0

Review Kling 3.0 on Kyeo AI: 3–15 seconds, single-shot or up to 5 multi-shots, first/last frames, sound, and std/pro/4k per-second rates. A fit for specifying first and last frames or splitting a 3–15-second concept into up to 5 short shots. Character consistency, lip sync, text, sound, and shot continuity still require review of the actual result.

AI video model
42–1005 credits / request

Veo3.1 Fast

Veo3.1 Fast on Kyeo AI supports text, first/last-frame and reference-image generation, direct 720p/1080p/4K selection, and 4/6/8-second duration controls. 30 / 38 / 90 credits by resolution.

AI video model
30 / 38 / 90 credits by resolution

Seedance 2.5

Seedance 2.5 combines a 30-second boundary, higher media counts, and video-editing reference input in one strict scene contract. Automatic duration is not underestimated at the 5-second default; Kyeo preauthorizes against the 30-second maximum.

AI video model
102–5,700 credits

Sources

This page is based on vendor materials, model-family documentation, and Kyeo AI integration settings.

Source note

1–15 seconds; 480p or 720p; up to 7 reference images。The selected resolution rate is multiplied by 1–15 seconds and rounded up: 480p costs 3–36 and 720p 5–68 credits, for an overall 3–68 range.

Last updated: 2026-08-28
xAI: Grok Imagine API
Official

Source — xAI: Grok Imagine API: The current 1.5 Preview workflow can generate native audio with the video.

Open original source
xAI: Grok Imagine Video 1.5
Official

Source — xAI: Grok Imagine Video 1.5: This is the current Grok Imagine Video 1.5 Preview generation page, not a compatibility layer for the legacy Grok Imagine routes.

Open original source
xAI: Video API reference
Official

Source — xAI: Video API reference for the current generation capabilities and request limits.

Open original source