Wan 2.2 I2V 480p Ultra Fast
Playground
Try it on WavespeedAI!Wan 2.2 A14B Image-to-Video (i2v-480p) produces ultra-fast 480p videos from single images, enabling unlimited AI video generation with high throughput. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Wan-2.2-i2v-480p-ultra-fast
wan-2.2/i2v-480p-ultra-fast is the ultra-fast, optimized version of Wan 2.2, designed for image-to-video (I2V) generation at 480p resolution. It leverages an innovative Mixture of Experts (MoE) architecture, combining high-noise and low-noise experts across denoising timesteps, enabling faster rendering while maintaining cinematic quality.
Why it looks great
- Cinematic Aesthetics – integrates professional film standards, controlling lighting, color, and composition.
- Natural Motion – handles large-scale, complex movements with smoothness and controllability.
- Semantic Precision – understands complex scenes and multi-object interactions, staying true to creative intent.
- Ultra-fast Performance – optimized pipeline ensures faster turnaround without sacrificing visual fidelity.
Limits and Performance
- Resolution: 480p
- Duration: 5s or 8s
Pricing
| Video Length | Cost (USD) |
|---|---|
| 5 seconds | $0.05 |
| 8 seconds | $0.08 |
Billing Rules:
- Minimum charge: 5 seconds
- Per-second rate: $0.01
- Total cost = video length × $0.01
How to Use
- Upload image – the keyframe (first frame) or reference image for video generation.
- (Optional) Upload last_image – to guide video generation.
- Enter prompt – describe scene, camera motion, style, or action.
- (Optional) Set negative_prompt – exclude unwanted elements.
- Choose duration – default 5s, adjustable for longer clips.
- Set seed – use -1 for randomness, or fix a number for reproducibility.
- Click Run – rendering begins, optimized for ultra-fast output.
Pro Tips
- Combine image + prompt for stronger consistency.
- Keep prompts detailed (motion, mood, lighting) for cinematic effect.
- Fix seed for reproducibility, change seed for variety.
- Use short clips for best speed-to-quality balance.
Note
When uploading an image, please check if the URL is accessible.
- If the URL is invalid or blocked, the model will not be able to load the image.
- A valid image URL will display a preview in the interface.
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/wavespeed-ai/wan-2.2/i2v-480p-ultra-fast" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"duration": 5,
"seed": -1
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| image | string | Yes | - | The image for generating the output. | |
| last_image | string | No | - | - | The last image for generating the output. |
| prompt | string | Yes | - | The positive prompt for the generation. | |
| negative_prompt | string | No | - | The negative prompt for the generation. | |
| duration | integer | No | 5 | 5, 8 | The duration of the generated media in seconds. |
| seed | integer | No | -1 | -1 ~ 2147483647 | The random seed to use for the generation. -1 means a random seed will be used. |
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 |