vidu/2.0/reference-to-image
Vidu 2.0 Reference To Image is Shengshu's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runvidu/2.0/reference-to-imageInput Schema
4 parameters · 1 required · 3 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | Text prompt for video generation, max 1500 characters · Max length: 1500 |
seed | integer | Optional | Random seed for generation |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16 |
reference_image_urls | string[] | Optional | URLs of the reference images to use for consistent subject appearance |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "vidu/2.0/reference-to-image",
"prompt": "The little devil is looking at the apple on the beach and walking around it.",
"reference_image_urls": [
"https://static.sandbase.ai/examples/shengshu/vidu/2.0/reference-to-image/input_reference_image_urls_0.png",
"https://static.sandbase.ai/examples/shengshu/vidu/2.0/reference-to-image/input_reference_image_urls_1.png",
"https://static.sandbase.ai/examples/shengshu/vidu/2.0/reference-to-image/input_reference_image_urls_2.png"
]
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Vidu 2.0 Reference to Image
Vidu 2.0 Reference to Image is centered on the vidu/2.0/reference-to-image workflow for reference to image work in image production. Vidu 2.0 Reference To Image is Shengshu's intelligent image editing model. Transform, retouch, and reimagine existing images using text prompts - from background replacement to artistic style conversion. Teams can place this named operation inside review, asset preparation, and publishing pipelines while keeping the original request attached to every result. The endpoint is especially useful when a project has a defined transformation goal and needs a repeatable request contract instead of an ad-hoc desktop step. Because vidu/2.0/reference-to-image is a separate catalog entry, evaluations should use this route’s own inputs, output expectations, and billing behavior. This is the creative remit of the exact endpoint, not a family-wide promise.
Vidu 2.0 Reference to Image exposes seed, prompt, aspect_ratio, reference_image_urls as its documented request surface. The mandatory portion is prompt. seed controls random seed for generation; prompt controls text prompt for video generation, max 1500 characters; aspect ratio controls the aspect ratio of the generated image; aspect ratio accepts 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16; reference image urls controls uRLs of the reference images to use for consistent subject appearance. For example, the route documentation includes “The little devil is looking at the apple on the beach and walking around it.”. Applications can submit that exact shape asynchronously, retain the chosen arguments in job metadata, and collect the resulting media URL for review or publishing.
Highlights
- Prompt-responsive composition. Vidu 2.0 Reference to Image turns detailed natural-language art direction into a complete visual with a defined subject, setting, and treatment.
- Style range. The route can interpret photographic, illustrative, graphic, or conceptual direction when those choices are stated clearly in the prompt.
- Layout control. Supported framing and composition controls help Vidu 2.0 Reference to Image prepare imagery for landscape, square, portrait, or design-specific placements.
- Iteration-ready output. Seed and other declared creative controls make it practical to compare focused variations while retaining the core brief.
Pricing
| Billing option | Price |
|---|---|
| Per request | $0.100000 |
When to Use
| Scenario | Why it fits |
|---|---|
| Choose Vidu 2.0 Reference to Image | Use it when the job specifically calls for reference to image and the route’s documented input contract matches assets already available in your workflow. |
| Keep the request reproducible | Use the required prompt explicitly, then record optional choices alongside the prompt for repeatable reruns. |
| Build controlled creative variations | Change one declared control at a time when comparing framing, format, duration, resolution, style, or other route-supported output decisions. |
| Integrate asynchronous delivery | Use this endpoint when an application can submit work, track completion, and collect the returned media URL instead of requiring an immediate inline artifact. |
| Validate before a large batch | Run representative prompts and source assets first, confirm the visual or audio behavior, then lock the successful request shape for scaled production. |
Prompt Guide
Lead with the subject or transformation, then add the composition, environment, style, lighting, motion, voice, or fidelity details relevant to this route. Keep every parameter inside the documented schema; the example below uses only fields declared for vidu/2.0/reference-to-image.
{
"prompt": "The little devil is looking at the apple on the beach and walking around it.",
"aspect_ratio": "21:9"
}
Technical Specs
| Specification | Details |
|---|---|
| Model ID | vidu/2.0/reference-to-image |
| Execution mode | async |
| Task type | image |
seed | integer · optional |
prompt | string · required |
aspect_ratio | string · optional · choices: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 |
reference_image_urls | array · optional |