Animate a first frame, optionally toward a last frame, into a 2-20 second 720p or 1080p video with native audio.
Provider: Lightricks
Category: video generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Animate a first frame, optionally toward a last frame, into a 2-20 second 720p or 1080p video with native audio.
Pricing
Standard Usage
Use images to control the first and last frame.
Ready for generation
Configure your parameters and click "Run" to see the output here.
Compare the input frames with the clips; prompts describe only the motion and sound added.
The first frame is a still landscape; the prompt only adds surf, gulls and a slow push-in while the subject stays put.
Prompt
Waves crash against the rocks below the lighthouse, seagulls glide across the golden sky, the camera slowly pushes in, sound of surf and gulls
Two frames, day and night: the model fills in the sky darkening, windows lighting up and the aurora appearing, with a locked camera.
Prompt
Time passes from bright winter day to starry night, the sky darkens, the cabin windows light up warmly and smoke rises from the chimney, an aurora appears, fixed camera
A vertical first frame with 9:16 output and audio off — clean footage for your own soundtrack.
Prompt
The potter's hands shape the spinning clay vase, it rises smoothly, wet clay glistens, slow subtle camera drift
The product shot is the first frame: petals fall, the camera orbits and light glints across the glass, with soft piano.
Prompt
Rose petals drift down around the perfume bottle, a slow orbit of the camera, light glints across the amber glass, soft piano
Landscape, vertical, sound-on and silent clips from the same model — tap to play.
Latte art
Muted by default — tap the speaker for sound
Coastal skate
Muted by default — tap the speaker for sound
Sneaker drop
Muted by default — tap the speaker for sound
Glowing forest
Muted by default — tap the speaker for sound
Sizzling dumplings
Muted by default — tap the speaker for sound
Future city aerial
Muted by default — tap the speaker for sound
Headphone ad
Muted by default — tap the speaker for sound
Alpine lake aerial
Muted by default — tap the speaker for sound
Rainy street musician
Muted by default — tap the speaker for sound
Lighthouse at golden hour
Muted by default — tap the speaker for sound
Latte art pour
Muted by default — tap the speaker for sound
Red fox in autumn woods
Muted by default — tap the speaker for sound
Slow-motion swish
Muted by default — tap the speaker for sound
Future megacity
Muted by default — tap the speaker for sound
Snowy cartoon bear
Muted by default — tap the speaker for sound
Balloon over terraces
Muted by default — tap the speaker for sound
Choose by input and need:
Choose it when: You only have a written idea
Trade-off: The prompt decides the subject
Choose it when: You want negative prompts and adherence control
Trade-off: 5 or 10 s only
Choose it when: You need 4:3, 3:4 or 1:1
Trade-off: First frame only, 720p
Current price: View live pricing
Two resolutions cover drafts and finals; length and frame combine freely.
| Setting | 720p | 1080p |
|---|---|---|
| Good for | Drafts, social, batch runs | Finals, ads, large screens |
| Length | 2-20 s | 2-20 s |
| Frame | 16:9 / 9:16 | 16:9 / 9:16 |
| Frame rate | 25fps | 25fps |
| Per-second price | Base tier | About 2× the 720p rate |
| Aspect | Text-to-video | Image-to-video |
|---|---|---|
| Input | Text prompt | First frame (optional last frame) + prompt |
| Control | Set by the prompt | Subject and composition locked by the image |
| Typical use | Ideation, previz | Product motion, transitions, animated posters |
| Model ID | ltx-2.5-fast/text-to-video | ltx-2.5-fast/image-to-video |
The first image opens the clip, the second closes it; similar compositions blend best.
Write only the change to add, not what is already shown.
Check the result in the Playground, then use the request below.
01
One clause each; the model generates picture and sound together.
Example:A barista pours latte art, close-up, morning light, soft clinking cups
02
Push-in, tracking, orbit, overhead or locked-off beats "dynamic".
Example:tracking shot from behind, low angle
03
The frame already sets subject and scene; describe only what moves.
Example:waves crash below, gulls glide, slow push-in
04
Similar composition gives smoother transitions; say what happens in between.
Example:time passes from day to night, windows light up, fixed camera
curl --request POST 'https://api.hiapi.ai/v1/tasks' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "ltx-2.5-fast/image-to-video",
"input": {
"prompt": "Waves crash against the rocks below the lighthouse, seagulls glide across the golden sky, the camera slowly pushes in, sound of surf and gulls",
"image_urls": [
"https://static.hiapi.ai/gallery/2026/10/0ca26560398eae72.jpg"
],
"resolution": "720p",
"duration": 6,
"aspect_ratio": "16:9",
"generate_audio": true
}
}'About LTX 2.5 Fast Image to Video
LTX 2.5 Fast Image to Video locks subject and composition with the first frame; the prompt adds motion, camera and sound. Add a last frame and the model fills in the journey between them, such as day to night.
720p or 1080p, 2-20 seconds, 16:9 or 9:16; native audio is on by default and turning it off does not change the price.
Each block shows the input image and the clip: the image sets subject and framing, the prompt adds motion, camera and sound.
Landscape photo
From the same lighthouse photo, the prompt asks for a dolly along the cliff with a slight upward tilt; surf, gulls and sunlight move on top of the original.
Compared with the earlier push-in example, changing only the prompt gives a different camera path.
Food content
A frame from a text-to-video clip becomes the first frame; the prompt adds the pour, the rosetta forming and rising steam with a gentle push-in.
Text first, then image: a handy way to extend a frame you like into more shots.
Wildlife
A lateral dolly creates parallax through trunks and mist while the fox blinks, flicks its tail and looks up as a leaf spirals down.
Leaves, brook and a distant bird arrive in sync — no separate ambience track needed.
Cartoon character
Cartoon art works too: the bear shifts its weight, waves and turns toward the moon as snow falls and the camera pushes in.
Gentle motion and a stable character design suit picture books, greetings and mascot clips.
Travel aerial
A still sunrise over terraces gains a forward track and slight rise as egrets lift off and mist drifts through the light.
Wind, creaking ropes and distant bells add a sense of place.
With two aligned frames the model fills in light, sky and smoke changes while the camera stays steady.
View this exampleThe lighthouse and rocks stay as shot; only surf, gulls and a push-in are added.
View this exampleUse a catalogue shot as the first frame and add an orbit, falling petals and soft music while the product keeps its shape.
View this exampleA 9:16 first frame gives vertical video; switch audio off to add your own soundtrack.
View this example
Product shots or a sentence become clips with sound.
9:16 output ready for feeds and short-video apps.
Up to 20-second takes to check pacing and camera.
First and last frames for day-to-night or seasonal changes.
One API key covers both text-to-video and image-to-video; task history keeps clips and charges together for review and cost tracking.
720p and 1080p, with 720p as the default, for both text-to-video and image-to-video.
2 to 20 seconds: 2, 3, 4, 5, 6, 8, 10, 12, 14, 16, 18 or 20, with 6 as the default.
Yes. Set aspect_ratio to 9:16 for vertical output; the default is 16:9 landscape.
With generate_audio on (the default) the model also creates ambience, effects or music. Turning it off gives a silent clip at the same price.
Per second of video; the per-second rate depends on resolution, and 1080p costs more than 720p. See the pricing page for current prices.
Use text-to-video when you only have an idea; use image-to-video when you already have a product shot, poster or storyboard frame and want tighter control of the subject.
Pass two images in image_urls; the second is the last frame. The model moves naturally from the first to the last frame — good for day-to-night or open/close transitions.
JPG, PNG or WebP image URLs. The closer the composition and camera position of the two frames, the smoother the transition.
It is fixed at 25fps; no parameter is needed.
The output frame is set by aspect_ratio. Match it to the first frame to avoid cropping or padding.
Use subject + action + camera + sound, e.g. "a barista pours latte art, close-up, morning light, soft clinking cups". For image-to-video, describe only the motion to add.
Result links expire. Download or copy clips to your own storage if you need to keep them.