Wan 2.7 Image to Image
alibaba/wan/2.7/image-to-imageAlibaba Wan 2.7 image-to-image model that edits images from a natural-language instruction, with multi-reference support and selectable aspect ratio.
- Base price
- $0.03USD / run
- Execution
- async
- Model type
- image
- Input fields
- 3
Try the model
Playground
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Your output will appear here
Complete the inputs, then click Run.
Specifications
Pricing
- Base price
- $0.03 / run
- Billing formula
- 0.03
Context & modalities
- Input
- Schema-defined
- Output
- image
Capabilities
- Chat
- Not supported
- Vision
- Not supported
- Reasoning
- Not supported
- Structured output
- Not supported
- Function calling
- Not supported
- Audio input
- Not supported
Access
- Provider
- Alibaba
- Model ID
- alibaba/wan/2.7/image-to-image
- Execution
- async
- API
- Unified Run API
- Endpoint
- /v1/run
API README
Wan 2.7 Image to Image
Wan 2.7 Image to Image applies Wan 2.7 understanding to still-image revision, changing requested content while keeping the source composition and identity cues available for continuity. It can rework objects, setting, styling, text, illumination, or presentation without forcing the creator to reconstruct the entire visual from scratch.
Describe the edit in terms of the desired final image, and explicitly name the people, products, geometry, or graphic elements that must stay stable. This model fits campaign localization, product variations, scene relighting, wardrobe changes, and art-direction iterations where source fidelity remains important.
Highlights
- Semantic image transformation. Changes object meaning, scene context, or artistic treatment through natural-language direction.
- Unrequested-content retention. Preserves important subjects and layout outside the intended revision.
- Context-matched reconstruction. Makes new content agree with the source perspective, material, color, and illumination.
- Iterative creative refinement. Supports successive corrections while maintaining continuity with the evolving image.
Pricing
| Configuration | Billing unit | Price |
|---|---|---|
| Base generation | Per request | $0.03 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The project needs this exact image editing workflow | The intended task belongs to a different media route |
| Available source media matches every required field | Required assets or usage rights are unavailable |
| The brief can define subject, action, camera, and style | Output must be deterministic at frame or pixel level |
| Supported duration, resolution, and framing fit delivery | Final placement requires unsupported specifications |
| An asynchronous generation job fits production | A live or frame-synchronous response is mandatory |
Prompt Guide
Describe the result as a shot or design brief: identify subjects and references, state the action or transformation, specify environment and composition, then add camera behavior, lighting, pacing, style, sound, and preservation constraints where relevant. Use exact reference identifiers exposed by the local schema.
{
"aspect_ratio": "21:9",
"images": [
"https://example.com/reference-1.png",
"https://example.com/reference-2.png"
],
"prompt": "Convert this photograph into a delicate watercolor painting style with visible brush strokes and soft color bleeding"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | alibaba/wan/2.7/image-to-image |
| Input fields | images (array)<br>prompt (string)<br>aspect_ratio (string; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, 9:21) |
| Required input | prompt, images |
| Output fields | url, content_type |
| Execution | Asynchronous job |
Related Models
alibaba/wan/2.7/text-to-image— Compare this concrete local family route.alibaba/wan/2.7/video-edit— Compare this concrete local family route.alibaba/wan/2.7/image-to-video— Compare this concrete local family route.
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/wan/2.7/image-to-image",
"images": [
"https://static.sandbase.ai/samples/image-editing/edit-style-watercolor-source.png"
],
"prompt": "Convert this photograph into a delicate watercolor painting style with visible brush strokes and soft color bleeding"
}
SANDBASE_JSON
)
run_id=$(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"Choose your model
Compare models
| Model | Type | Default price | Released |
|---|---|---|---|
Wan 2.7 Image to ImageThis model Alibaba | Image | $0.03 / run | Apr 1, 2026 |
Alibaba | Image | $0.04 / run | Jul 21, 2026 |
Alibaba | Image | $0.04 / run | Jul 21, 2026 |
Alibaba | Image | $0.07 / run | Apr 1, 2026 |
Alibaba | Image | $0.03 / run | Apr 1, 2026 |
Alibaba | Image | $0.07 / run | Apr 1, 2026 |
Questions
FAQ
How do I call Wan 2.7 Image to Image through SandBase?
Create a SandBase API key, then send requests with the model ID "alibaba/wan/2.7/image-to-image" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.
Do I need a separate Alibaba account?
No. One SandBase API key and balance gives you access to Wan 2.7 Image to Image and the other models in the catalog; you do not need to sign up with Alibaba separately.