Wan 2.1 T2V 480p Ultra Fast
Playground
Try it 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.
Features
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 | $0.01875/s |
Prompting tips (T2V)
- Write like a director: Subject + Action + Scene + Camera + Style
- Use concrete motion verbs: walks, turns, reaches, leans, spins, drifts, stops
- Add camera language to make it feel like “video,” not “animated still”: slow dolly-in, handheld, orbit, pan left, tilt up, rack focus
- Keep negative prompts short and practical: blurry, jittery, flicker, distorted, low quality, inconsistent motion
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"size": "832*480",
"num_inference_steps": 30,
"duration": 5,
"guidance_scale": 5,
"flow_shift": 3,
"seed": -1
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/t2v-480p-ultra-fast" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| negative_prompt | string | No | - | The negative prompt for the generation. | |
| size | string | No | 832*480 | 832*480, 480*832 | The size of the generated media in pixels (width*height). |
| num_inference_steps | integer | No | 30 | 0 ~ 40 | The number of inference steps to perform. |
| duration | integer | No | 5 | 5 ~ 10 | The duration of the generated media in seconds. |
| guidance_scale | number | No | 5 | 0 ~ 20 | The guidance scale to use for the generation. |
| flow_shift | number | No | 3 | 1 ~ 10 | The shift value for the timestep schedule for flow matching. |
| seed | integer | No | -1 | - | 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 | Output values, usually URL strings; some models return text strings or structured result objects (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.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 |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| 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 |