seedinteger
Random seed for reproducible results.
Wan 2.6 Image to Image
alibaba/wan/2.6/image-to-imageAlibaba Wan 2.6 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.
Random seed for reproducible results.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "aspect_ratio": "9:16", "images": [ "https://static.sandbase.ai/examples/6bc956c9-0728-4ee7-aa97-d02ad81fa8fb/input/24863bca-7df6-4e54-b38c-b93467a50f16.png" ], "prompt": "Turn the scene into a snowy winter night", "seed": 7 }
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
- #38 of 77
- Elo
- 1044 ±13
- Gap to #1
- −155
Image-editing arena: people pick the better of two edits of the same image and instruction, without seeing the model names.
- #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
- #41Wan 2.71042±13
- #42HunyuanImage 3.0 (Tencent Cloud)1029±16
Wan 2.6 Image to Image
Wan 2.6 image editing: send one or more pictures and describe the change, such as a restyle, object swap, or new background.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 10,000 characters. |
images | image URL[], required | — | Images to edit or combine, 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. |
seed | integer | random | Fix it to compare prompt changes. |
Billing
$0.03 per output image, Alibaba's list price. Input images are not metered.
| Request | Price |
|---|---|
| One image | $0.03 |
Failed runs are not charged.
Prompting
- State the change and what must stay the same.
Limits
- One output image per request. Wan 2.7 image-to-image is the newer model at the same price.
Also on SandBase
Other Wan 2.6 endpoints: alibaba/wan/2.6/text-to-video, alibaba/wan/2.6/image-to-video, alibaba/wan/2.6/reference-to-video, alibaba/wan/2.6/flash/image-to-video, alibaba/wan/2.6/flash/reference-to-video, alibaba/wan/2.6/text-to-image, alibaba/wan/2.7/text-to-video (newer), alibaba/wan/2.7/image-to-image (newer, same price).
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/2.6/image-to-image",
"images": [
"https://static.sandbase.ai/samples/image-editing/edit-style-watercolor-source.png"
],
"prompt": "Convert this photograph into a delicate watercolor painting style with visible brush strokes and soft color bleeding"
}
SANDBASE_JSON
)
run_id=$(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
List of input image URLs for editing. Up to 4 images.
promptstringrequired
The editing instruction describing what changes to make.
Default: "Convert this photograph into a delicate watercolor painting style with visible brush strokes and soft color bleeding"
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/2.6/image-to-image",
"images": [
"https://static.sandbase.ai/samples/image-editing/edit-style-watercolor-source.png"
],
"prompt": "Convert this photograph into a delicate watercolor painting style with visible brush strokes and soft color bleeding"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "Self organization completed prediction",
"source_url": "https://www.sandbase.ai",
"url": "https://static.sandbase.ai/examples/6bc956c9-0728-4ee7-aa97-d02ad81fa8fb/output/bdee4692-2f0f-4704-a379-643bfb2f9a20.png"
}
]