WAN 2.1 T2V 480p Ultra-Fast turns text prompts into unlimited 480p AI videos with ultra-fast throughput and reliable 480p output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.125per run·~80 / $10
ExamplesView all
A man on top of a jumping bull at a rodeo party, he is dressed as a cowboy with a cowboy hat.
Ultra realistic 8k miniature world scene with mini Easter bunnies working on building a giant chocolate egg. Some bunnies are on ladders decorating the egg with colorful candies, others are driving tractors and carts carrying chocolate pieces. There are shovels and toy tools scattered around. The environment is cheerful, with flowers, giant carrots in the background, blue sky and spring weather. Cute, magical, detailed and cinematic style.
Guerra celestial entre anjos com espada no céu com relâmpagos.
the girl is talking and smiling
"A esposa de Ló, contra o aviso dos anjos, olha para trás e é instantaneamente transformada em uma estátua de sal. Seu corpo petrificado, com expressão de terror, permanece no deserto, enquanto Ló e suas filhas fogem, sem ousar voltar."
An ancient Japanese temple nestled in a bamboo forest, misty morning, traditional architecture, harmonious colors, peaceful ambiance, volumetric lighting, digital painting.
A majestic lion roaring, golden mane flowing, against a backdrop of the African savanna, dust rising, golden hour, wildlife photography, powerful, dynamic.
A steampunk city at night, with glowing gears and steam plumes rising from intricate clockwork towers. Airships with brass propellers drift lazily across a starry sky. The streets are wet from rain, reflecting the neon signs.
An elderly artisan with calloused hands meticulously carving intricate details into a wooden sculpture in his sunlit workshop. Wood shavings curl around his tools, and a faithful dog naps peacefully by his feet.
A tranquil mountain lake at dawn, mist gently rising from the glassy surface. A lone wooden rowboat drifts slowly near the shore, reflecting the soft pastel colors of the rising sun and the distant snow-capped peaks
An elderly couple dancing slowly and gracefully on a seaside promenade at sunset, their silhouettes against the fiery orange sky. The gentle ocean breeze plays with their clothes, and the waves softly lap the shore in the background.
A curious red fox tiptoeing through a snow-covered winter wonderland. Its fluffy tail brushes the fresh powder, and its keen eyes scan the silent landscape for movement. Sunlight sparkles on the snow.
Related Models
README
Wan 2.1 T2V 480p Ultra Fast — wavespeed-ai/wan-2.1/t2v-480p-ultra-fast
Wan 2.1 T2V 480p Ultra Fast is a text-to-video model optimized for speed and iteration. Write a prompt, pick a duration, and generate a short 480p video quickly—ideal for rapid concept testing, storyboard previews, and high-volume variations.
What it’s good at
- Text-to-Video (T2V): generate video directly from a prompt
- Ultra-fast generation: built for quick iteration and high-throughput workflows
- 480p output: lightweight resolution for draft-quality previews and batch runs
- Creative control knobs: guidance scale, steps, flow shift, seed
Common use cases
- Storyboard & pre-visualization: turn scripts into short motion sketches before committing to higher-cost renders
- Marketing concept exploration: generate multiple variants of the same idea (camera, action, mood) and pick winners fast
- Motion style prototyping: test different motion intensity settings for pacing, dynamism, and scene continuity
- Batch ideation: generate many drafts to explore composition, timing, and cinematic language
Inputs
- Prompt (required): describe subject, action, setting, lighting, camera movement, and mood
- Negative prompt (optional): list artifacts to avoid (blur, jitter, distortion, low quality, inconsistent motion)
Parameters (Playground / API)
- Size: 832×480 (480p)
- Duration: 5s or 10s
- Num inference steps: higher can improve stability/detail but costs more time
- Guidance scale: higher follows the prompt more strictly; too high may reduce natural motion
- Flow shift: adjusts motion feel and temporal dynamics
- Seed: use a fixed value for reproducibility; use -1 for random
Pricing
| Output | Duration | Price per video | Price per second |
|---|---|---|---|
| 480p T2V Ultra Fast | 5s | $0.125 | $0.0250/s |
| 480p T2V Ultra Fast | 10s | $0.1875 | $0.01875/s |
Prompting tips (T2V)
- Write like a director: Subject + Action + Scene + Camera + Style
- Use concrete motion verbs: walks, turns, reaches, leans, spins, drifts, stops
- Add camera language to make it feel like “video,” not “animated still”: slow dolly-in, handheld, orbit, pan left, tilt up, rack focus
- Keep negative prompts short and practical: blurry, jittery, flicker, distorted, low quality, inconsistent motion
Wan 2.1 T2v 480p Ultra Fast API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/t2v-480p-ultra-fast 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 2.1 T2v 480p Ultra Fast below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/t2v-480p-ultra-fast" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"num_inference_steps": 30,
"duration": 5,
"guidance_scale": 5,
"flow_shift": 3,
"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("wavespeed-ai/wan-2.1/t2v-480p-ultra-fast", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"num_inference_steps": 30,
"duration": 5,
"guidance_scale": 5,
"flow_shift": 3,
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/wan-2.1/t2v-480p-ultra-fast",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"num_inference_steps": 30,
"duration": 5,
"guidance_scale": 5,
"flow_shift": 3,
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.1 T2v 480p Ultra Fast API — Frequently asked questions
What is the Wan 2.1 T2v 480p Ultra Fast API?
Wan 2.1 T2v 480p Ultra Fast is a WaveSpeedAI model for video generation, exposed as a REST API on WaveSpeedAI. WAN 2.1 T2V 480p Ultra-Fast turns text prompts into unlimited 480p AI videos with ultra-fast throughput and reliable 480p output. 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 2.1 T2v 480p Ultra Fast 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/wavespeed-ai/wan-2.1-t2v-480p-ultra-fast.
How much does Wan 2.1 T2v 480p Ultra Fast cost per run?
Wan 2.1 T2v 480p Ultra Fast starts at $0.13 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 2.1 T2v 480p Ultra Fast accept?
Key inputs: `prompt`, `duration`, `size`, `seed`, `guidance_scale`, `num_inference_steps`. 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/wavespeed-ai/wan-2.1-t2v-480p-ultra-fast.
How long does Wan 2.1 T2v 480p Ultra Fast take to generate?
Average end-to-end generation time on WaveSpeedAI is around 41 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 2.1 T2v 480p Ultra Fast outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.