seedinteger
Random seed (0-2147483647) for reproducible results. Omit for a random seed.
Minimum: 0
Maximum: 2147483647
Wan 2.7 Video Extend
alibaba/wan/2.7/video-extendAlibaba Wan 2.7 Video Extend continues an input clip from a text instruction, optionally ending on a chosen last frame, for a total length of up to 15 seconds.
Try the model
Playground
Input
What happens after the source clip ends: action, camera movement, scene progression, and sound. Up to 5,000 characters.
URL of the source clip to continue (MP4 or MOV, 2-10 seconds, 240-4096px per side, up to 100MB).
Additional Settings More
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Optional last frame the continuation should end on (JPEG, PNG, BMP, or WebP; 240-8000px per side, up to 20MB).
Total length of the output in seconds, including the source clip (2-15). For a 3-second source and duration 10, the model adds 7 seconds. Must be longer than the source clip. Allowed values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
The resolution of the video to generate. Allowed values: 720p, 1080p.
Random seed (0-2147483647) for reproducible results. Omit for a random seed. Range: 0 to 2147483647.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "prompt": "The baker brings over the glazed bread, sets the brush aside, and the camera follows him to the oven at the back to bake it. The baker closes the oven door, stands beside it watching the bread, smells the aroma, and says, \"so good\".", "video": "https://static.sandbase.ai/examples/e1e1d989-70de-4368-b8d6-3a0919be90be/input/3627aff0-af0f-4067-813d-02de847a28b4.mp4" } - Open result ↗
Input
{ "duration": 10, "end_image": "https://static.sandbase.ai/examples/6f0aa006-092a-4928-81a6-8dcc540a5f94/input/e647b006-fde3-461d-a97d-a712a7795369.webp", "prompt": "The man looks down at the wooden box on the ground. He bends over, carefully opens the lid, and stares at the contents. His lips tremble and part slightly, his brow furrows, and his eyes widen with a horrified expression.", "video": "https://static.sandbase.ai/examples/6f0aa006-092a-4928-81a6-8dcc540a5f94/input/7e501c4f-2478-49c6-8697-64d8c44400a7.mp4" }
Wan 2.7 Video Extend
Continue an existing clip. Wan 2.7 picks up from the last frame of video and generates new footage that follows your prompt; add end_image to say where the continuation should land.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 5,000 characters. |
video | video URL, required | — | Clip to continue. |
end_image | image URL | — | Optional frame the new footage should end on. |
duration | 2–15 | 5 | Length of the new footage in seconds. |
resolution | 720p / 1080p | 720p | Sets the per-second rate. |
seed | integer 0–2147483647 | random | Fix it to compare prompt changes. |
Billing
You pay for output seconds: $0.10 at 720p and $0.15 at 1080p, the same as Alibaba's list price. Only the new footage is billed.
| New footage | 720p | 1080p |
|---|---|---|
| 2s | $0.20 | $0.30 |
| 5s (default) | $0.50 | $0.75 |
| 10s | $1.00 | $1.50 |
| 15s | $1.50 | $2.25 |
Failed runs are not charged.
Prompting
- Describe what happens next, not what is already in the clip.
- Match the source's camera style unless you want a deliberate change.
- Use
end_imagewhen the shot must finish on a specific composition.
Limits
- The returned video contains the continuation; join it to the source in your editor if you need one file.
Also on SandBase
Other Wan 2.7 endpoints: alibaba/wan/2.7/text-to-video, alibaba/wan/2.7/image-to-video, alibaba/wan/2.7/reference-to-video, alibaba/wan/2.7/video-edit, alibaba/wan/3.0/video (newer, up to 30s).
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/2.7/video-extend",
"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/hfugmr/wan-r2v-role1.mp4",
"prompt": "A girl takes a selfie in the mirror, then picks up her backpack and walks out of the room.",
"duration": 5,
"resolution": "720p"
}
SANDBASE_JSON
)
run_id=$(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
videostringrequired
URL of the source clip to continue (MP4 or MOV, 2-10 seconds, 240-4096px per side, up to 100MB).
promptstringrequired
What happens after the source clip ends: action, camera movement, scene progression, and sound. Up to 5,000 characters.
durationinteger
Total length of the output in seconds, including the source clip (2-15). For a 3-second source and duration 10, the model adds 7 seconds. Must be longer than the source clip.
Default: 5
Possible values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
end_imagestring
Optional last frame the continuation should end on (JPEG, PNG, BMP, or WebP; 240-8000px per side, up to 20MB).
resolutionstring
The resolution of the video to generate.
Default: "720p"
Possible values: "720p", "1080p"
{
"model": "alibaba/wan/2.7/video-extend",
"video": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260129/hfugmr/wan-r2v-role1.mp4",
"prompt": "A girl takes a selfie in the mirror, then picks up her backpack and walks out of the room.",
"duration": 5,
"resolution": "720p"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/7dd835e57bac8c025b9d.jpg",
"source": "Alibaba Cloud",
"source_url": "https://www.alibabacloud.com/help/en/model-studio/wan-image-to-video-guide",
"url": "https://static.sandbase.ai/examples/e1e1d989-70de-4368-b8d6-3a0919be90be/output/99a0b1f2-d458-425e-8666-39b03bf9cc58.mp4"
}
]