imagesarrayrequired
List of input image URLs for editing. Up to 4 images.
Wan 2.7 Pro Image to Image
alibaba/wan/2.7/pro/image-to-imageAlibaba Wan 2.7 Pro image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.
Try the model
Playground
Input
The editing instruction describing what changes to make.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
List of input image URLs for editing. Up to 4 images.
Additional Settings More
Customize your input with more control.
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21.
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/b6b5c008-4e2b-443b-a9ce-2fcf162ecdb1/input/53727e1f-7615-415c-b23b-2afcd51b167a.webp" ], "prompt": "Edit based on image 1. Replace the raspberry selected in box 1 with a lemon, the raspberry in box 2 with a strawberry, and the raspberry in box 3 with a blueberry. The result should be harmoniously integrated with the original image, without the reference boxes and numbers, and keep the rest of the content unchanged." } - Open result ↗
Input
{ "images": [ "https://static.sandbase.ai/examples/4edfb8e5-a83b-47fc-9ff3-2764e41487c8/input/3f453edf-2a53-4ec4-8c0a-f3109581ae39.webp" ], "prompt": "Please generate a set of four Polaroid photos with the theme \"Seasonal Changes\". Each photo is taken at the same location, under a tree in a park, but shows the scenes of spring, summer, autumn, and winter respectively. The person's attire should also match the season: a light jacket in spring, a short-sleeved shirt in summer, a trench coat in autumn, and a scarf and thick coat in winter. Place this set of photos on a dining table." } - Open result ↗
Input
{ "images": [ "https://static.sandbase.ai/examples/b6784267-a660-4ca5-8f02-8e1632103a5b/input/8bf3bbc9-8c95-4aa8-9df3-e23e52acb9c4.webp" ], "prompt": "Extract the clothing items from the uploaded photo and arrange them in a flat-lay display on a pure white background. Maintain realistic details and material textures. Fashion e-commerce style, suitable for clothing display." } - Open result ↗
Input
{ "images": [ "https://static.sandbase.ai/examples/6ea41cfa-7caf-4f99-82eb-b9b3f69165b2/input/5e329c11-64d7-4bcf-88ad-6bc085bb7c04.webp" ], "prompt": "Casually write \"Time for Holiday?\" on the sand with a hand." } - Open result ↗
Input
{ "images": [ "https://static.sandbase.ai/examples/03f79ad0-5c89-4ced-bb0c-bc6f3168fe2c/input/da26bcee-7731-4aa4-9dfe-0b287e5bd0b2.webp" ], "prompt": "Keep the person's features unchanged and generate front, side, and back views." } - Open result ↗
Input
{ "images": [ "https://static.sandbase.ai/examples/8a27df1b-431e-4b6b-b786-ca30b5b414f8/input/0546190f-782a-462e-8bc4-d7ac703002d3.webp" ], "prompt": "Reshoot this photo with a fisheye lens." }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Image Editing
- Rank
- #36 of 77
- Elo
- 1050 ±13
- Gap to #1
- −149
Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.
- #31Qwen-Image-2.1-Turbo1064±14
- #32HunyuanImage 3.0 Instruct1063±13
- #33Seedream 5.0 Lite1062±13
- #34Qwen Image 2.0 Pro (2026-04-22)1058±17
- #35Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)1054±12
- #36Wan 2.7 Pro1050±13
- #37DreamImage 2.01048±13
- #38Wan 2.6 Image1044±13
- #39Luma UNI 11043±13
- #40Seedream 4.51043±13
Wan 2.7 Pro Image to Image
The Pro tier of Wan 2.7 image editing: the same instruction-based edits as the standard tier, rendered with more detail and better preservation of faces, text, and fine texture.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 10,000 characters. |
images | image URL[], required | — | Images to edit or combine, referred to as Image 1, Image 2, … |
aspect_ratio | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 9:21 | — | Omit to follow the first input image. |
Billing
$0.075 per output image, Alibaba's list price. Input images are not metered.
| Request | Price |
|---|---|
| One image | $0.075 |
Failed runs are not charged.
Prompting
- Lead with the edit, then list what must not change.
- Describe light and color for relighting edits: “dramatic sunset, long shadows, warm light on the walls”.
Limits
- One output image per request.
Also on SandBase
Other Wan 2.7 image endpoints: alibaba/wan/2.7/text-to-image, alibaba/wan/2.7/image-to-image, alibaba/wan/2.7/pro/text-to-image.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/2.7/pro/image-to-image",
"images": [
"https://static.sandbase.ai/samples/image-editing/edit-time-of-day-source.png"
],
"prompt": "Change the time to dramatic sunset with orange and purple sky, long shadows, warm golden light on the lighthouse"
}
SANDBASE_JSON
)
run_id=$(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
promptstringrequired
The editing instruction describing what changes to make.
Default: "Change the time to dramatic sunset with orange and purple sky, long shadows, warm golden light on the lighthouse"
aspect_ratiostring
The aspect ratio of the generated image.
Possible values: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16", "9:21"
{
"model": "alibaba/wan/2.7/pro/image-to-image",
"images": [
"https://static.sandbase.ai/samples/image-editing/edit-time-of-day-source.png"
],
"prompt": "Change the time to dramatic sunset with orange and purple sky, long shadows, warm golden light on the lighthouse"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "Alibaba Cloud",
"source_url": "https://www.alibabacloud.com/help/en/model-studio/wan-image-edit",
"url": "https://static.sandbase.ai/examples/b6b5c008-4e2b-443b-a9ce-2fcf162ecdb1/output/46e6059b-1776-4312-a1a6-cd3fe7be1782.webp"
}
]