LTX-2 is an AI creative engine for production workflows, generating synchronized audio and 1080p video output (cost $0.06/s). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.06per run·~16 / $1
ExamplesView all
A cinematic, epic fantasy video, bringing the climactic duel from the input image to life. The scene starts with the static standoff: Harry Potter and Lord Voldemort locked in their spell clash amidst the ruins of Hogwarts, exactly as seen in the image. Their wands tremble under the immense power. The magic intensifies. Voldemort's deadly green Avada Kedavra curse and Harry's powerful golden Expelliarmus spell violently push against each other. The central vortex of clashing magic pulses erratically, spitting out sparks. Debris and dust levitate and swirl. Voldemort, his face contorted with rage, snarls through gritted teeth (implied): "You cannot win, Potter!" Harry grits his teeth, his expression one of extreme strain but unwavering determination. He shouts back defiantly (implied): "Never!" Immediately after the implied lines, Harry pushes with renewed force, the golden light flares, briefly overpowering the green.
A cinematic, epic fantasy video, starting from the input image. The scene begins with the warrior woman standing stoically on the snowy mountain peak, as seen in the image. Snowflakes swirl gently around her, and her fur cloak flutters slightly in the icy wind. She slowly turns her head, her gaze piercing and determined, looking out towards the vast, unseen valley below (off-camera) as if facing an insurmountable challenge. Her expression hardens with resolve. She then raises her colossal warhammer, slowly and deliberately, bringing it to rest on her armored shoulder. The hammer's head, intricately carved with runes, glints under the dim, overcast sky. The camera slowly zooms out, revealing the immense scale of the snowy, treacherous mountain range around her, emphasizing her solitary, defiant stance against the harsh elements. Her breath condenses in the cold air.
Cinematic fantasy video starting from the input image. The warrior woman stands stoically on the snowy peak. Suddenly, an ancient dwarven rune carved into the rock beneath the snow at her feet flares with intense, cold blue magical energy. This unleashes a localized vortex of swirling snow and ice particles around her. She instinctively grips her massive warhammer tighter, bracing herself against the arcane power, eyes narrowed. Camera slightly pushes in as the vortex erupts. Style: Photorealistic, masterpiece, high detail, dramatic lighting, magical particle effects, slow-motion effect on vortex.
A cinematic, high-intensity chase sequence, bringing the input image to thrilling life. The scene continues the desperate escape. The red Jeep bounces violently on the muddy jungle track, engine roaring, struggling to outrun the massive T-Rex thundering just behind it. Mud and debris fly. The T-Rex gains ground, letting out a deafening roar that shakes the trees and the camera slightly. Cut to a tight, shaky close-up inside the Jeep. The driver grips the steering wheel white-knuckled, his face drenched in sweat, eyes wide with terror. He glances frantically into the vibrating rearview mirror (or quickly over his shoulder). His mouth opens wide in a desperate, panicked shout (implied): "Damn! Damn!" The camera cuts back immediately to a low-angle shot from behind the Jeep, showing the T-Rex's massive, clawed foot crashing down dangerously close to the vehicle's rear tire. Style: Photorealistic, high detail, intense action, motion blur, suspenseful, shaky cam effect, masterpiece.
A cinematic, intensely suspenseful video, bringing the input image to life with subtle, real-time animation. The scene *holds* on the climactic standoff: the knight kneels defiant, sword raised high, mouth open in a continuous shout, locked in a tense face-off with the colossal, menacing dragon amidst the fiery ruins, exactly as pictured. Subtle movements animate the tension: The dragon's massive head looms, its glowing red eyes *intently focused* on the knight. A low, guttural growl *rumbles* (implied sound). Thick saliva/blood *drips* from its maw, *sizzling* on the hot debris. Its breath creates faint heat haze. The knight holds his ground, muscles visibly *trembling* with strain. His defiant shout continues (mouth remains open), breath *ragged*. His eyes, filled with fierce determination, *do not waver*. The environment breathes with danger: Flames *flicker violently* in the background ruins, casting *dancing shadows*. Embers *float and drift* through the air. Small pieces of debris *occasionally shift and fall*. Camera: *Maintains the composition* similar to the image, perhaps with a *very slight, almost imperceptible tremor* to enhance the tension. Style: Photorealistic, masterpiece, high detail, extreme tension, dark fantasy, cinematic lighting (high contrast, firelight).
Related Models
README
lightricks/ltx-2-pro/image-to-video 🎬✨
LTX-2 Pro is a flagship AI creative engine by Lightricks, designed for real production workflows that demand precision, synchronization, and cinematic realism. This model transforms a single image and a descriptive prompt into a dynamic, story-driven video — complete with synchronized motion and audio cues.
🌟 Key Features
-
🎞 Image-to-Video Magic Bring static images to life with natural motion, lighting shifts, and cinematic camera moves — turning a single frame into a full narrative moment.
-
🎧 Audio–Video Synchronization Generates perfectly timed motion and atmosphere, matching the rhythm and emotion implied by your prompt or soundtrack.
-
🚀 Production-Ready Quality Built for professional pipelines — ensuring stable motion, clear detail, and controlled style consistency across frames.
-
🎨 Context-Aware Generation Understands visual composition and preserves the original image’s tone, colors, and spatial relationships while expanding motion naturally.
-
🧩 Adaptive Cinematic Control Handles camera direction, subject focus, and environmental motion (dust, fog, lighting) with impressive smoothness.
⚙️ Parameters
| Parameter | Description |
|---|---|
| prompt* | Describe the intended scene, mood, or action. Example: “A cinematic fantasy duel surrounded by swirling magic and glowing ruins.” |
| image* | Upload a static image (JPG / PNG) to serve as the visual base for animation. |
| duration | Video length in seconds (6s / 8s / 10s). |
💰 Pricing
| Target Resolution | Price per second | Approx. Runtime per $1 |
|---|---|---|
| 1080p | $0.06 / s | ~17 seconds per $1 |
💡 Use Cases
- Cinematic Storytelling — Animate still concept art or keyframes into short sequences.
- Marketing & Trailers — Turn product shots or artwork into motion-rich promotional clips.
- Film & Game Previsualization — Generate dynamic previews from environment or character stills.
- Music & Mood Videos — Sync visual motion with ambient or thematic sound design.
Ltx 2 Pro Image To Video API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/lightricks/ltx-2-pro/image-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Ltx 2 Pro Image To Video below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/lightricks/ltx-2-pro/image-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 6,
"generate_audio": true
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("lightricks/ltx-2-pro/image-to-video", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 6,
"generate_audio": true
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"lightricks/ltx-2-pro/image-to-video",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"duration": 6,
"generate_audio": true
}
)
print(output["outputs"][0]) # → URL of the generated outputLtx 2 Pro Image To Video API — Frequently asked questions
What is the Ltx 2 Pro Image To Video API?
Ltx 2 Pro Image To Video is a Lightricks model for video generation from images, exposed as a REST API on WaveSpeedAI. LTX-2 is an AI creative engine for production workflows, generating synchronized audio and 1080p video output (cost $0.06/s). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Ltx 2 Pro Image To Video API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/lightricks/lightricks-ltx-2-pro-image-to-video.
How much does Ltx 2 Pro Image To Video cost per run?
Ltx 2 Pro Image To Video starts at $0.060 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Ltx 2 Pro Image To Video accept?
Key inputs: `prompt`, `image`, `duration`, `generate_audio`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/lightricks/lightricks-ltx-2-pro-image-to-video.
How long does Ltx 2 Pro Image To Video take to generate?
Average end-to-end generation time on WaveSpeedAI is around 88 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Ltx 2 Pro Image To Video outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Lightricks). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.