fpsinteger
The frame rate of the generated video.
Default: 16
Minimum: 1
Maximum: 60
Wan Alpha
alibaba/wan/alphaWan Alpha is Alibaba's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.
Try the model
Playground
Input
The prompt to guide the video generation.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
The resolution of the generated video. Allowed values: 240p, 360p, 480p, 720p.
Advanced settings
The seed for the random number generator.
The output type of the generated video. Allowed values: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif).
Whether to binarize the mask.
160
The frame rate of the generated video. Range: 1 to 60.
01
The threshold for mask binarization. When binarize_mask is True, this threshold will be used to binarize the mask. This will also be used for transparency when the output type is `.webm`. Range: 0 to 1.
01
The upper bound of the mask clamping. Range: 0 to 1.
01
The lower bound of the mask clamping. Range: 0 to 1.
ResultIdle
Your output will appear here
Complete the inputs, then click Run.
Wan Alpha
Wan Alpha creates professional text-to-video clips from scripts and descriptive prompts, emphasizing realistic motion, lighting, and scene composition. It serves as an exploratory Wan generation model for converting narrative ideas into moving visual concepts without requiring a source image or reference clip.
Use a complete scene description with subject, action, environment, camera position, movement, time of day, lighting, and mood. It works best for concept development and cinematic ideation where the creator wants the model to invent the full visual world rather than preserve an existing asset.
Highlights
- Script-to-scene translation. Turns written narrative direction into a staged moving sequence.
- Realistic motion rendering. Produces subject and environmental movement intended to feel physically connected.
- Lighting-aware cinematography. Builds illumination and atmosphere into the generated scene rather than adding them as flat style labels.
- Composed visual storytelling. Coordinates subject placement, background, camera, and action into a readable shot.
Pricing
| Resolution | Price per generated second |
|---|---|
| 240p | $0.010 |
| 360p | $0.010 |
| 480p | $0.020 |
| 720p | $0.040 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The project needs this exact multimodal creation workflow | The intended task belongs to a different media route |
| Available source media matches every required field | Required assets or usage rights are unavailable |
| The brief can define subject, action, camera, and style | Output must be deterministic at frame or pixel level |
| Supported duration, resolution, and framing fit delivery | Final placement requires unsupported specifications |
| An asynchronous generation job fits production | A live or frame-synchronous response is mandatory |
Prompt Guide
Describe the result as a shot or design brief: identify subjects and references, state the action or transformation, specify environment and composition, then add camera behavior, lighting, pacing, style, sound, and preservation constraints where relevant. Use exact reference identifiers exposed by the local schema.
{
"fps": 16,
"prompt": "A cinematic scene with clearly directed subject action, camera movement, lighting, pacing, and atmosphere",
"resolution": "240p",
"seed": 1
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | alibaba/wan/alpha |
| Input fields | fps (integer; 1–60)<br>seed (integer)<br>prompt (string)<br>resolution (string; 240p, 360p, 480p, 720p)<br>aspect_ratio (string; 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16)<br>binarize_mask (boolean)<br>mask_clamp_lower (number; 0–1)<br>mask_clamp_upper (number; 0–1)<br>video_output_type (string; X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif))<br>mask_binarization_threshold (number; 0–1) |
| Required input | prompt |
| Output fields | url, content_type |
| Execution | Asynchronous job |
Related Models
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/alpha",
"fps": 16,
"prompt": "Medium shot. A little girl holds a bubble wand and blows out colorful bubbles that float and pop in the air. The background of this video is transparent. Realistic style.",
"resolution": "480p",
"binarize_mask": false,
"mask_clamp_lower": 0.1,
"mask_clamp_upper": 0.75,
"video_output_type": "VP9 (.webm)",
"mask_binarization_threshold": 0.8
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
seedinteger
The seed for the random number generator.
promptstringrequired
The prompt to guide the video generation.
resolutionstring
The resolution of the generated video.
Default: "480p"
Possible values: "240p", "360p", "480p", "720p"
aspect_ratiostring
The aspect ratio of the generated image.
Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16"
binarize_maskboolean
Whether to binarize the mask.
Default: false
mask_clamp_lowernumber
The lower bound of the mask clamping.
Default: 0.1
Minimum: 0
Maximum: 1
mask_clamp_uppernumber
The upper bound of the mask clamping.
Default: 0.75
Minimum: 0
Maximum: 1
video_output_typestring
The output type of the generated video.
Default: "VP9 (.webm)"
Possible values: "X264 (.mp4)", "VP9 (.webm)", "PRORES4444 (.mov)", "GIF (.gif)"
mask_binarization_thresholdnumber
The threshold for mask binarization. When binarize_mask is True, this threshold will be used to binarize the mask. This will also be used for transparency when the output type is `.webm`.
Default: 0.8
Minimum: 0
Maximum: 1
{
"model": "alibaba/wan/alpha",
"fps": 16,
"prompt": "Medium shot. A little girl holds a bubble wand and blows out colorful bubbles that float and pop in the air. The background of this video is transparent. Realistic style.",
"resolution": "480p",
"binarize_mask": false,
"mask_clamp_lower": 0.1,
"mask_clamp_upper": 0.75,
"video_output_type": "VP9 (.webm)",
"mask_binarization_threshold": 0.8
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
No example output has been published yet. Use Playground → Result → JSON after a completed run to inspect your response.