grok-imagine-video-1.5 (Official)

by xAIVideo

Official-channel Grok 1.5 image-to-video generation with first-frame input and 480P, 720P, or 1080P output.

InputPrompttext
Models1available
FlowAsyncresult URL
Price4.8 quota480P official output
Example clip9:16 portrait preview
Example clip

15s, 9:16, photorealistic romantic POV video, natural real-life couple moment. Continue naturally from the original image. Preserve her face, white dress, hairstyle, body proportions, garden and warm afternoon sunlight. She gently holds the viewer's hand and begins walking forward along the stone garden path, naturally pulling the camera with her. Her long hair moves realistically in the warm breeze. She looks back over her shoulder with a soft playful smile. She says naturally: "Come on, you're walking too slow." The camera follows behind with realistic footsteps and subtle handheld movement. She laughs softly and gives the viewer's hand a playful little tug. Off-camera male voice: "Where are you taking me?" She keeps walking, turns back again and smiles: "It's a surprise." Male: "That's what you said last time." She laughs: "Just trust me." She slows down slightly, looks back into the camera and says: "Close your eyes." Male: "Absolutely not." She laughs and pulls his hand again: "Come on!" End while they continue walking together into the garden. CAMERA: authentic first-person boyfriend POV, realistic walking movement, natural handheld imperfections, no cinematic floating camera. PERFORMANCE: spontaneous chemistry, natural laughter, blinking, breathing, eye contact, small head movements and realistic hand interaction. ENVIRONMENT: gentle breeze moving her hair and dress, leaves and flowers moving subtly, changing sunlight through trees. AUDIO: natural female voice, off-camera male voice, footsteps, birds, leaves, soft wind and distant outdoor ambience. No subtitles, no cuts, no slow motion, no exaggerated acting.

Image to video · Official · 15s · 1152 × 2048 · 9:16 portrait
Examples

Prompt to video, in context

01 · Garden hand-in-handI2V
Prompt

15s, 9:16, photorealistic romantic POV video, natural real-life couple moment. Continue naturally from the original image. Preserve her face, white dress, hairstyle, body proportions, garden and warm afternoon sunlight. She gently holds the viewer's hand and begins walking forward along the stone garden path, naturally pulling the camera with her. Her long hair moves realistically in the warm breeze. She looks back over her shoulder with a soft playful smile. She says naturally: "Come on, you're walking too slow." The camera follows behind with realistic footsteps and subtle handheld movement. She laughs softly and gives the viewer's hand a playful little tug. Off-camera male voice: "Where are you taking me?" She keeps walking, turns back again and smiles: "It's a surprise." Male: "That's what you said last time." She laughs: "Just trust me." She slows down slightly, looks back into the camera and says: "Close your eyes." Male: "Absolutely not." She laughs and pulls his hand again: "Come on!" End while they continue walking together into the garden. CAMERA: authentic first-person boyfriend POV, realistic walking movement, natural handheld imperfections, no cinematic floating camera. PERFORMANCE: spontaneous chemistry, natural laughter, blinking, breathing, eye contact, small head movements and realistic hand interaction. ENVIRONMENT: gentle breeze moving her hair and dress, leaves and flowers moving subtly, changing sunlight through trees. AUDIO: natural female voice, off-camera male voice, footsteps, birds, leaves, soft wind and distant outdoor ambience. No subtitles, no cuts, no slow motion, no exaggerated acting.

02 · Neon supercar commercialT2V
Text-to-video · no reference image
Prompt

Create a 15-second cinematic automotive commercial. FORMAT: 15 seconds, 9:16 vertical, 720p, photorealistic, cinematic realism. 0–4s: A glossy black supercar sits motionless on a rain-soaked neon street at night. Heavy rain falls across the bodywork, forming realistic droplets and reflections. The LED headlights suddenly illuminate through the mist. 4–9s: The engine starts and the car accelerates forward. The camera tracks extremely low beside the front wheel as water sprays naturally from the tires. Neon signs streak beautifully across the reflective bodywork. 9–13s: The supercar enters a fast sweeping corner. The camera dynamically follows from a low rear three-quarter angle while realistic tire spray and road reflections emphasize speed. 13–15s: The camera drops behind the vehicle as it accelerates into the neon city, red taillights disappearing through rain and atmospheric mist. CAMERA: low-angle tracking shots, smooth dolly movement, subtle speed ramp, realistic motion blur, cinematic anamorphic lens flare. LIGHTING: neon reflections, wet asphalt reflections, dramatic rim lighting, atmospheric volumetric mist. Premium automotive advertising, realistic vehicle physics, physically accurate suspension and tire rotation, highly detailed paint reflections, cinematic HDR, professional commercial color grading. Avoid vehicle deformation, changing car design, warped wheels, unrealistic reflections, floating objects, flickering, unstable geometry, excessive camera shake or sudden scene changes.

03 · Mechanical watch macroT2V
Text-to-video · no reference image
Prompt

Create a premium 15-second luxury watch commercial. FORMAT: 15 seconds, 9:16 vertical, 720p, ultra-photorealistic product cinematography. 0–4s: A luxury mechanical watch slowly emerges from darkness. A narrow beam of light travels across the polished metal case, revealing microscopic brushed-metal texture. 4–8s: The camera moves into an extreme macro shot of the dial. The second hand moves smoothly while tiny mechanical details catch subtle highlights. 8–12s: Transition toward the transparent mechanical movement. Gears rotate with precise realistic motion while reflections move naturally across sapphire crystal and polished metal. 12–15s: Pull back as the complete watch slowly rotates toward the camera and settles into an elegant hero position. CAMERA: 100mm macro lens aesthetic, extremely shallow depth of field, slow controlled orbital movement, precise rack focus. LIGHTING: premium studio lighting, controlled specular highlights, deep shadows, elegant reflections. Luxury advertising aesthetic, physically accurate materials, realistic glass refraction, microscopic metal details, cinematic contrast, smooth motion. No warped typography, no changing watch geometry, no floating components, no flickering, no unrealistic reflections.

04 · Alien desert discoveryT2V
Text-to-video · no reference image
Prompt

Create an epic 15-second cinematic science-fiction sequence. FORMAT: 15 seconds, 9:16 vertical, 720p, photorealistic cinematic realism. 0–4s: A lone astronaut slowly walks across an enormous alien desert. Fine dust rises naturally beneath each boot. A gigantic blue planet dominates the sky. 4–8s: The camera follows closely behind the astronaut while subtle wind moves dust across the landscape. The astronaut suddenly notices something ahead and slows down. 8–12s: The camera gradually rises over the astronaut's shoulder, revealing an enormous mysterious alien structure emerging from atmospheric fog on the horizon. 12–15s: The astronaut stops and looks upward while the camera continues pulling back, emphasizing the overwhelming scale of the structure. CAMERA: cinematic tracking shot transitioning into a dramatic crane reveal, subtle handheld realism, strong foreground-to-background depth. LIGHTING: distant sunlight, atmospheric scattering, volumetric dust, realistic spacesuit reflections. Epic scale, realistic gravity, detailed spacesuit materials, physically accurate dust simulation, IMAX science-fiction cinematography, cinematic HDR. Avoid cartoon aesthetics, distorted astronaut anatomy, floating movement, flickering structures, unstable environment or unrealistic physics.

05 · Morning latte ritualT2V
Text-to-video · no reference image
Prompt

Create a luxurious 15-second coffee commercial. FORMAT: 15 seconds, 9:16 vertical, 720p, photorealistic macro cinematography. 0–3s: Fresh roasted coffee beans fall in dramatic slow motion onto a dark wooden surface, tiny particles floating naturally through warm morning light. 3–7s: Extreme macro shot of espresso flowing smoothly from a professional machine into a transparent glass. Rich crema gradually forms across the surface. 7–11s: Silky steamed milk pours into the espresso, creating beautiful swirling patterns with physically accurate liquid dynamics. 11–15s: A perfect latte sits beside a sunlit window. Steam rises slowly while the camera gently pushes toward the cup. CAMERA: macro lens, slow-motion details, smooth push-in, elegant rack focus, shallow depth of field. LIGHTING: warm morning sunlight, soft volumetric rays, beautiful highlights through steam. Realistic liquid physics, detailed crema, natural steam simulation, premium café advertising, cinematic bokeh, commercial food photography. Avoid unrealistic liquid behavior, disappearing objects, cup deformation, excessive steam, flickering or morphing.

06 · Golden fragrance campaignT2V
Text-to-video · no reference image
Prompt

Create an elegant 15-second luxury fragrance campaign. FORMAT: 15 seconds, 9:16 vertical, 720p, cinematic photorealism. 0–4s: An elegant woman stands inside a minimalist luxury interior illuminated by soft golden light. She slowly turns toward the camera while a gentle breeze moves her hair naturally. 4–8s: The camera smoothly circles around her as she raises a beautifully designed perfume bottle. 8–12s: Focus transitions from her eyes toward the perfume bottle. Light passes through the glass, creating realistic refraction and delicate highlights. 12–15s: Extreme product close-up. The perfume bottle rests elegantly in her hand while the background falls into creamy cinematic bokeh. CAMERA: 85mm portrait lens aesthetic, slow orbital movement, shallow depth of field, elegant rack focus. LIGHTING: soft diffused golden light, delicate rim lighting, luxury studio highlights. High-fashion cinematography, realistic skin texture, natural hair physics, realistic glass refraction, sophisticated commercial color grading. Maintain consistent facial identity, hands and product geometry. Avoid extra fingers, distorted hands, facial morphing, warped bottle geometry, flickering or unnatural motion.

Capabilities

What you can build with grok-imagine-video-1.5 (Official)

Prompt driven generation

Submit a concise prompt and get production-ready video output through one TTAPI job.

Core controls only

Keep integration simple with prompt, model, output settings, and callback handling.

Async result flow

Use polling or webhook callbacks so long-running generations do not block your UI.

Ready for product UI

Return grok-imagine-video-1.5 (Official) results that can be displayed, stored, or passed into downstream workflows.

Pricing

Per-action, in quota

Usage is metered in quota by model, action, and output settings.

Official channel pricingOfficial pricing
Input / outputPriceUnit
Input image0.6 quota/ image
480P output4.8 quota/ second
720P output8.4 quota/ second
1080P output15 quota/ second
API request

grok-imagine-video-1.5 (Official) operations and request fields

Use the endpoint below with your TTAPI key and the request fields shown.

Generate officialPOST
/grok/v1/videos/generations

Submit an official-channel Grok task with duration, image, reference_images, and resolution.

Official reference
Fetch officialGET
/grok/v1/videos/{request_id}

Retrieve an official-channel Grok video result by request_id.

Official reference
Extend officialPOST
/grok/v1/videos/extensions

Extend an official Grok video with prompt, source video, duration, and model.

Official reference
POSThttps://api.ttapi.io/grok/v1/videos/generations

Headers

TT-API-KEYstringrequired

Your TTAPI API key.

Content-Typestringrequired

Use application/json.

Body

promptstringconditional

Required for grok-imagine-video text-to-video; optional for grok-imagine-video-1.5 image-to-video.

modelenumoptional

Defaults to grok-imagine-video-1.5. Supported: grok-imagine-video and grok-imagine-video-1.5.

aspect_ratioenumoptional

1:1, 16:9, 9:16, 4:3, 3:4, 3:2, or 2:3.

durationinteger | stringoptional

Defaults to 8 seconds. Accepts 1–15 as either a number or a numeric string.

imageobjectconditional

Image input object for image-to-video. Required by grok-imagine-video-1.5 and optional for the base model.

reference_imagesobject[]optional

Reference-image objects for the reference-to-video workflow.

resolutionenumoptional

480p, 720p, or 1080p.

voice_idenumoptional

Voice role ID for the generated video audio. Options include carina, zagan, helix, orion, luna, iris, altair, and zenith.

Open the official TTAPI documentation
Integrate

From key to first result

Copy the resolved endpoint, authentication headers, and request body for this model.

curl --request POST \
  --url https://api.ttapi.io/grok/v1/videos/generations \
  --header 'TT-API-KEY: $TTAPI_KEY' \
  --header 'Content-Type: application/json' \
  --data '{"prompt":"a contemporary dancer in a sculptural gray costume under a narrow spotlight","model":"grok-imagine-video-1.5","aspect_ratio":"9:16","duration":6,"image":{"url":"https://example.com/first-frame.jpg"},"resolution":"1080p","voice_id":"luna"}'