Leonardoai Motion 2.0
Playground
Try it on WavespeedAI!Leonardo Motion 2.0 delivers upgraded image-to-video generation, producing more realistic, detailed videos than its predecessor. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Leonardo Motion 2.0
Generate smooth, cinematic video from a single prompt (and optional reference image). Motion 2.0 focuses on stable subjects, clean transitions, and faster turnaround—ideal for story beats, product shots, title cards, and social posts.
Why it looks great
- Enhanced motion coherence — Sharper continuity between subject and background with far less flicker, wobble, or geometric distortion.
- Stable subject integrity — Characters and objects keep their identity under complex moves; no “melting” during fast action.
- Higher aesthetic quality — Cinematic lighting, richer textures, and finer detail for a more filmic look and stronger sense of depth.
- Improved motion control — Prompts like “slow dolly-zoom” or “rapid orbit” map more faithfully to the final camera behavior.
- Faster generation — Quicker inference so you can iterate rapidly and lock creative decisions sooner.
Pricing
$0.30 per run! Clear, simple pricing for predictable budgeting.
How to use
- Write your prompt. Describe scene, subject, motion, lighting, and mood.
- (Optional) Add a reference image.
- Pick aspect_ratio.
16:9for landscape,9:16for vertical. - Generate. Review the result, then refine phrasing (or reuse the same seed if available) for controlled iterations.
Prompt starters
- “A lone hiker at golden hour; slow dolly-in, gentle wind in grass, soft rim light, shallow depth of field, cinematic grade.”
- “Minimal product hero on pedestal; 360° orbit at medium speed, studio key light + soft fill, glossy reflections.”
- “Noir alley at night; handheld micro-jitter and push-in, neon bounce light, light rain, fog rolling through.”
Pro tips
- Be explicit about camera verbs (dolly, pan, tilt, orbit) and speed (slow/medium/fast).
- Specify lighting and materials (backlight, rim light, volumetrics, glossy/rough) to guide mood and texture.
- Keep prompts focused; remove conflicting style words to improve motion coherence.
- When using an image, describe which parts should stay consistent versus change.
Common use cases
- Storyboards and previz with believable camera language
- Logo/title motion with controlled cinematic moves
- Product promos that preserve brand color and surfaces
- Social shorts where vertical 9:16 is a must
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/leonardoai/motion-2.0" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"aspect_ratio": "16:9"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| image | string | No | - | The image to be used for image generation. | |
| aspect_ratio | string | No | 16:9 | 16:9, 9:16 | The aspect ratio of the generated media. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |