xAI · Video model

Grok Imagine in Twistavo AI Studio

Grok Imagine is xAI's family of image and video generation models. Twistavo AI Studio offers Grok Imagine 2.0, Grok Image and Grok Imagine Video 1.5. The cheapest run costs 9 credits: Grok Image at 1K, quoted before you confirm.

Try Grok Imagine

Facts checked

Credits

Credit quote per run at each variant's default settings: one image, or one clip at the default length and resolution named in the row. Your exact quote appears in AI Studio before you confirm.
VariantCredits
Grok Imagine 2.022 credits
Grok Image9 credits
Grok Imagine Video 1.5193 credits for a 5 s clip at 720p

Shorter clips cost fewer credits. AI model prices lists each model from its shortest clip, so its numbers can be lower than the default-length quotes here.

Credits come from monthly plans and one-time extra credits for subscribers: see Pricing.

Versions compared

Versions in Twistavo AI Studio, credits per run as quoted today
VersionTypeLengthResolutionsFrame shapesInputsPrice per runWhat the maker says, and what Twistavo offers
Grok Imagine 2.0Image—2K1:1, 4:3, 3:4, 16:9, 9:16Prompt + reference images (up to 8)22 credits (2K)

xAI: grok-imagine-image-2.0 generates images from text or edits them from reference images. source

On Twistavo: inputs: prompt, reference images; 2K

Grok ImageImage—1K, 2K1:1, 1:2, 2:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16Prompt + reference images (up to 8)9 credits (1K) · 9 credits (2K)

On Twistavo: inputs: prompt, reference images; 1K and 2K

Grok Imagine Video 1.5Video4–10 sDefaultDefaultPrompt + reference images (up to 8)193 credits (5 s)

xAI: reference images bring specific people, objects or clothing into the clip, for virtual try-on, product placement and stories with recurring characters. source

On Twistavo: inputs: prompt, reference images; 4 to 10 seconds

Also in Twistavo AI Studio: Grok Imagine Video, for clips made from a prompt and a start frame, priced per tier.

Sources

Samples

AI-generated with Grok Imagine 2.0: A collage of the rooftops, bridges and fishing boats of a fictional harbour town in a stenciled street-art style on a concrete wall, three spray paint colours, no lettering, signs or logos
AI-generated with Grok Imagine 2.0A collage of the rooftops, bridges and fishing boats of a fictional harbour town in a stenciled street-art style on a concrete wall, three spray paint colours, no lettering, signs or logosaspectRatio 16:9, resolution 1kMade 2026-11-16Use this prompt
AI-generated with Grok Image: Photorealistic photograph of a fictional adult woodworker sanding a wooden chair in a sunlit workshop, sawdust in the air, natural skin texture, no text or logos
AI-generated with Grok ImagePhotorealistic photograph of a fictional adult woodworker sanding a wooden chair in a sunlit workshop, sawdust in the air, natural skin texture, no text or logosaspectRatio 3:4, resolution 1kMade 2026-11-16 · 9 credits at these settingsUse this prompt

Limits and known issues

  • Reference images guide who and what appears in a clip but do not lock its first frame (xAI). source
  • A prompt that leads with mood, film stock or a list of things to avoid tends to give a styled scene whose subject is a stand-in (xAI). source

How to get good results

  1. Open with one sentence naming the subject, its form, what holds it and the setting; mood and styling come after (xAI). source
  2. Name every key element and how many there are, such as two mugs or one person seen from the waist up (xAI). source
  3. Keep the same order in every prompt of a series: subject, details, art direction, light, colour, composition (xAI). source
  4. Keep the same frame shape across a series so the images sit together (xAI). source
  5. With many references, give each one a single role and a fixed place in the scene, keep the cast small and keep props static (xAI). source

Questions

Can the video model start from text?

No. In AI Studio it needs reference images or a source video, plus your prompt. The composer asks for them before quoting.

Which inputs are accepted?

Across the family: reference images. Limits per variant are listed in the table.

How long are the clips?

From 4 to 10 seconds, set with the duration control.

What makes a good reference set?

Sharp images with consistent light, the subject clearly visible and no text overlays. Show the character or product from the angles the clip needs, and leave out pictures that contradict each other in style.

Can I mix my own footage in?

Yes, the video model also reads short source videos. Use footage you own or have permission to use, and describe in the prompt which elements of it should be kept.

How much does Grok Imagine cost?

Prices per run in Twistavo AI Studio: Grok Imagine 2.0: 22 credits at 2K. Grok Image: 9 credits at 1K and 9 credits at 2K. Grok Imagine Video 1.5: 193 credits at 5 s.

Is Grok Imagine free?

Grok Imagine runs are paid in credits in Twistavo AI Studio. 1 free image after signup, no card (GPT Image 2.6, 1k). Videos need a plan. Plans from $3.99/month. Credits never expire and every generation is quoted before it starts.

Can Grok Imagine make videos?

Yes. Grok Imagine Video 1.5 makes clips of 4 to 10 seconds from your reference images and prompt. Grok Imagine Video 1.5: 193 credits at 5 s.

Grok Imagine is a trademark of xAI. Twistavo is an independent product, not affiliated with or endorsed by xAI; it offers the model through its AI provider. Facts on this page come from the AI Studio catalogue and may change with the provider.