WAN 2.2 t2v-plus-1080p converts text prompts into high-quality 1080p videos for unlimited AI video creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.8per run·~12 / $10
ExamplesView all
An older couple, seen from behind, sits on a wooden bench watching the sunset over the ocean. The man gently places his arm around the woman's shoulder. The scene is peaceful and filled with unspoken history. --Static wide shot, silhouette, warm golden hour colors, photorealistic, emotionally resonant.
At twilight, a couple in elegant, flowing white attire performs a slow, romantic dance on a sea of soft, pastel-colored clouds. The sky around them is a gradient of orange, pink, and purple. --Wide shot, dreamlike atmosphere, hyperrealistic cloud texture, cinematic color grading,
A beautiful woman with silver hair cries, and her tears transform into tiny, glowing crystals that fall and rest on her silk dress. The scene is illuminated only by the soft, ethereal light of a massive, detailed moon in the background. --Extreme close-up on her face, cinematic slow motion, magical realism, bokeh background, photorealistic details on the crystals.
A striking portrait of a person partially submerged in a pool of tranquil, molten gold. Their eyes are closed, and their face and shoulders, adorned with delicate jewelry, rise above the shimmering liquid surface. --Artistic close-up, high contrast, realistic liquid metal texture, serene and luxurious feel.
In a dark, ancient library, a young man opens a leather-bound book. As he does, golden particles of light rise from the pages, swirling around him and illuminating his face with wonder. --Medium shot, dramatic chiaroscuro lighting, high detail on dust and light particles, slow motion, magical and enchanting mood.
A lone figure in a dark cloak stands on a perfectly still, mirror-like lake at night. The water reflects a breathtaking, hyper-detailed nebula and galaxy in the sky above, making it seem as if they are standing in the middle of space. --Static wide shot, surreal and epic scale, high dynamic range (HDR), realistic reflections, 4K.
A woman's cupped hands gently open, releasing a single, magnificent butterfly whose wings are made of shimmering, liquid stained-glass. The butterfly takes flight in a sun-drenched, magical forest. --Extreme close-up on hands, then slow-motion tracking shot of the butterfly, vibrant colors, shallow depth of field.
A person stands on the edge of a cliff overlooking a sunset-drenched ocean. As the wind blows, the edges of their long, flowing cloak begin to fray and seamlessly transform into a flock of white doves that soar into the sky. --Medium shot transitioning to a wide shot, photorealistic visual effects, epic and symbolic, slow motion.
A point-of-view (POV) shot of someone holding a clear umbrella while walking down a rain-slicked city street at night. The neon signs of shops blur and reflect beautifully in the puddles on the pavement. --POV shot, hyperrealistic water effects, moody lighting, atmospheric.
Related Models
README
WAN 2.2 Text-to-Video Model (1080p)
WAN 2.2 is an advanced text-to-video (T2V) model powered by an MoE (Mixture of Experts) architecture. It generates cinematic-quality videos at Full HD 1080p resolution, supporting both landscape (1920×1080) and portrait (1080×1920) formats.
Why it looks great
- Cinematic quality: controls lighting, color, and camera composition for professional results.
- Smooth motion: handles subject and camera movement with stability and naturalness.
- Semantic alignment: faithfully follows detailed text prompts, even in complex scenes.
- Prompt expansion (optional): refine prompts automatically for enhanced output.
Limits and Performance
- Input: text prompt
- Output resolution: 1080p (1920×1080 or 1080×1920)
- Clip length per job: 5 seconds
Pricing
| Duration | Resolution | Cost per job |
|---|---|---|
| 5 s | 1080p | $0.80 |
How to Use
- Write Prompt – describe the scene, mood, motion, and camera style.
- Choose Size – landscape (1920×1080) or portrait (1080×1920).
- (Optional) Add a Negative Prompt to exclude unwanted details.
- (Optional) Set Seed for reproducibility.
- Run – preview and download your 5-second video.
Pro tips
- Use clear motion cues in the prompt (e.g., “slow pan”, “gentle breeze”).
- Choose portrait mode (1080×1920) for mobile/social content, landscape for cinematic use.
- Apply negative prompts to avoid artifacts like text, watermarks, or distortions.
- Enable prompt expansion if you want the system to refine under-specified prompts.
Notes
- Please check that your prompt and parameters are correct before running.
- If results don’t align, try re-running with different seeds.
Wan 2.2 T2v Plus 1080p API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/t2v-plus-1080p 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 Wan 2.2 T2v Plus 1080p below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/alibaba/wan-2.2/t2v-plus-1080p" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1920*1080",
"duration": 5,
"enable_prompt_expansion": false,
"negative_prompt": "blurry, low quality, distorted",
"seed": -1
}'
# 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("alibaba/wan-2.2/t2v-plus-1080p", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1920*1080",
"duration": 5,
"enable_prompt_expansion": false,
"negative_prompt": "blurry, low quality, distorted",
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"alibaba/wan-2.2/t2v-plus-1080p",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1920*1080",
"duration": 5,
"enable_prompt_expansion": false,
"negative_prompt": "blurry, low quality, distorted",
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.2 T2v Plus 1080p API — Frequently asked questions
What is the Wan 2.2 T2v Plus 1080p API?
Wan 2.2 T2v Plus 1080p is a Alibaba model for video generation, exposed as a REST API on WaveSpeedAI. WAN 2.2 t2v-plus-1080p converts text prompts into high-quality 1080p videos for unlimited AI video creation. 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 Wan 2.2 T2v Plus 1080p 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/alibaba/alibaba-wan-2.2-t2v-plus-1080p.
How much does Wan 2.2 T2v Plus 1080p cost per run?
Wan 2.2 T2v Plus 1080p starts at $0.80 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 Wan 2.2 T2v Plus 1080p accept?
Key inputs: `prompt`, `duration`, `size`, `seed`, `negative_prompt`, `enable_prompt_expansion`. 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/alibaba/alibaba-wan-2.2-t2v-plus-1080p.
How long does Wan 2.2 T2v Plus 1080p take to generate?
Average end-to-end generation time on WaveSpeedAI is around 84 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Wan 2.2 T2v Plus 1080p outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Alibaba). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.