seedinteger
Random seed (0-2147483647) for reproducible results. Omit for a random seed.
Wan 2.7 Reference to Video
alibaba/wan/2.7/reference-to-videoAlibaba Wan 2.7 reference-to-video model generating video guided by reference content.
Try the model
Playground
Input
The text prompt to generate a video from.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
The URLs of reference images to guide video generation. Provide at least one reference image or video.
Add at least one media item.
Additional Settings More
Customize your input with more control.
The URLs of reference videos to guide video generation.
The duration of the generated video in seconds. Allowed values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
The aspect ratio of the generated video. Allowed values: 16:9, 9:16, 1:1, 4:3, 3:4.
The resolution of the video to generate. Allowed values: 720p, 1080p.
Random seed (0-2147483647) for reproducible results. Omit for a random seed.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "images": [ "https://static.sandbase.ai/examples/6ec7122b-e121-4332-aac6-9564b61c6067/input/b1c60c74-e701-44d8-8f6a-c50b4cb6ffa0.webp" ], "prompt": "Reference image, 3D cartoon adventure movie style, chibi characters with detailed textures, smooth actions, and vibrant colors. Keep the characters and forest scene consistent. Do not add text. Atmosphere: Adventurous, lighthearted, mysterious, whimsical. Characters: Boy explorer: round hat, backpack, short cloak. Sidekick: a flying small robot with a round body and blue glowing eyes. Scene: Fantasy forest with giant tree roots, mushrooms, vines, a treasure cave entrance, and sunbeams. Storyboard: 1. Wide shot: Tall trees and interlaced light beams in a mysterious and bright fantasy forest. 2. Medium shot: The boy pushes aside vines to explore. 3. Medium shot: The small robot flies beside him, scanning ahead with a blue light. 4. Close-up: An old treasure map unfolds in the boy's hands. 5. Close-up: He shows an excited expression, his eyes lighting up. 6. Action shot: The two jump over tree roots and a stream, continuing deeper into the forest. 7. Medium shot: A moss-covered treasure chest is revealed behind the vines. 8. Close-up: A golden glow shines from the edge of the treasure chest. 9. Final shot: The boy and the small robot stand before the treasure chest, looking at each other in surprise, full of adventure." }
Wan 2.7 Reference to Video
Cast people, products, or characters from reference images (and optional reference videos) into a new scene. The prompt directs what they do; Wan 2.7 keeps their appearance consistent and supports several referenced characters interacting in one shot.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 50,000 characters. |
images | image URL[], required | — | Reference images, referred to in the prompt as Image 1, Image 2, … |
videos | video URL[] | — | Optional reference clips, referred to as Video 1, Video 2, … |
duration | 2–15 | 5 | Output length in seconds. |
aspect_ratio | 16:9 / 9:16 / 1:1 / 4:3 / 3:4 | — | Output frame shape. |
resolution | 720p / 1080p | 720p | Sets the per-second rate. |
seed | integer | 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. When you send reference videos, 5 seconds of input are added to the billed length.
| Output | 720p | 1080p |
|---|---|---|
| 5s, images only | $0.50 | $0.75 |
| 5s, with reference video | $1.00 | $1.50 |
| 10s, images only | $1.00 | $1.50 |
| 15s, images only | $1.50 | $2.25 |
Failed runs are not charged.
Prompting
- Give every reference a role: “Image 1 is the chef, Image 2 is the kitchen, Video 1 sets the camera move”.
- Numbering follows array order, so reordering
imageschanges what “Image 2” means. - Keep each reference image to one clear subject.
Limits
- The output is a new clip; to change an existing video use
alibaba/wan/2.7/video-edit.
Also on SandBase
Other Wan 2.7 endpoints: alibaba/wan/2.7/text-to-video, alibaba/wan/2.7/image-to-video, alibaba/wan/2.7/video-edit, alibaba/wan/2.7/video-extend, alibaba/wan/3.0/video (newer, up to 30s).
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/2.7/reference-to-video",
"images": [
"https://static.sandbase.ai/examples/alibaba/wan/2.6/reference-to-video/flash/input_images_0.png"
],
"prompt": "A golden retriever puppy running through a field of wildflowers in slow motion, ears flapping, tongue out, soft backlight",
"duration": 5,
"resolution": "720p"
}
SANDBASE_JSON
)
run_id=$(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
imagesarrayrequired
The URLs of reference images to guide video generation. Provide at least one reference image or video.
promptstringrequired
The text prompt to generate a video from.
Default: "A golden retriever puppy running through a field of wildflowers in slow motion, ears flapping, tongue out, soft backlight"
videosarray
The URLs of reference videos to guide video generation.
durationinteger
The duration of the generated video in seconds.
Default: 5
Possible values: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
resolutionstring
The resolution of the video to generate.
Default: "720p"
Possible values: "720p", "1080p"
aspect_ratiostring
The aspect ratio of the generated video.
Possible values: "16:9", "9:16", "1:1", "4:3", "3:4"
{
"model": "alibaba/wan/2.7/reference-to-video",
"images": [
"https://static.sandbase.ai/examples/alibaba/wan/2.6/reference-to-video/flash/input_images_0.png"
],
"prompt": "A golden retriever puppy running through a field of wildflowers in slow motion, ears flapping, tongue out, soft backlight",
"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/06a833ab909502d05a32.jpg",
"source": "Alibaba Cloud",
"source_url": "https://www.alibabacloud.com/help/en/model-studio/video-to-video-guide",
"url": "https://static.sandbase.ai/examples/6ec7122b-e121-4332-aac6-9564b61c6067/output/69588557-e71b-479f-9cd3-29ece3fc657d.mp4"
}
]