sandbase-ai/hy-wu-edit

Name: Hy Wu Edit
Author: sandbase-ai

Hy Wu Edit by sandbase-ai - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Input

Prompt(string)

The text prompt describing the desired edit. Supports both English and Chinese. Use specific instructions like 'Replace the clothing on figure 1 with the outfit from figure 2'.

Image URL or upload(array)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

URLs of input images for editing. Typically 2 images: the base image and the reference image. Supports up to 3 images.

Num Inference Steps(integer)

1100

Number of diffusion denoising steps. Range: 1 to 100.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Enable Thinking(boolean)

Enable thinking mode. The model reasons about the edit before generating, producing higher quality results at the cost of longer inference time. Disable for faster results on straightforward edits.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Seed(integer)

Random seed for reproducible results. If None, a random seed is used.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDsandbase-ai/hy-wu-edit

Input Schema

7 parameters · 1 required · 6 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The text prompt describing the desired edit. Supports both English and Chinese. Use specific instructions like 'Replace the clothing on figure 1 with the outfit from figure 2'.
`seed`	integer	Optional	Random seed for reproducible results. If None, a random seed is used.
`images`	string[]	Optional	URLs of input images for editing. Typically 2 images: the base image and the reference image. Supports up to 3 images.
`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
`output_format`	string	Optional	The format of the generated image. · Options: jpeg, png · Default: "png" jpegpng
`enable_thinking`	boolean	Optional	Enable thinking mode. The model reasons about the edit before generating, producing higher quality results at the cost of longer inference time. Disable for faster results on straightforward edits. · Default: true
`num_inference_steps`	integer	Optional	Number of diffusion denoising steps. · Min: 1 · Max: 100 · Default: 30

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, or timeout
Retrieve — Read outputs from 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": "sandbase-ai/hy-wu-edit",
  "images": [
    "https://static.sandbase.ai/examples/openai/gpt-image-1/edit/input_images_0.png",
    "https://static.sandbase.ai/examples/openai/gpt-image-1/edit/input_images_0.png"
  ],
  "prompt": "Using image 1 as the base image, replace the outfit with the clothing from image 2 while keeping the subject, pose, and background unchanged.",
  "output_format": "png",
  "enable_thinking": true,
  "num_inference_steps": 30
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Hy Wu Edit

API README

Hy Wu Edit

Hy Wu Edit occupies the guided-image-revision role in the model catalog for content pipeline engineers. Its practical value is to reduce ambiguity when a workflow chooses among neighboring model variants: an upstream service can confirm that it has prompt, submit one well-scoped job, and receive a revised image asset for downstream approval. This positioning explains when the exact sandbase-ai/hy-wu-edit route belongs in an architecture without borrowing promises from another version, tier, or task variant.

A low-risk adoption path begins by checking the source ownership, expected result, and release checklist. The caller records required values separately from optional choices such as seed, images, aspect_ratio, output_format, enable_thinking, num_inference_steps, runs a small representative sample, and stores the route name with the resulting artifact. Reviewers then compare that artifact with the agreed acceptance criteria, document any rejected setup, and promote only a successful request shape into larger batches. This workflow gives sandbase-ai/hy-wu-edit measurable business context while leaving the Highlights section to explain model behavior.

Highlights

Instruction-led revision. Hy Wu Edit applies a written change to supplied imagery instead of rebuilding the scene without visual context.
Source continuity. The edit workflow helps Hy Wu Edit retain recognizable composition and subject information while carrying out the requested transformation.
Targeted creative changes. Hy Wu Edit suits restyling, replacement, cleanup, and composition adjustments expressed in natural language.
Repeatable variants. Teams can keep the same source and vary one instruction at a time to compare controlled edit directions with Hy Wu Edit.

Pricing

Billing option	Price
Per request	`$0.100000`

When to Use

Scenario	Why it fits
Choose Hy Wu Edit	Use it when the job specifically calls for hy wu edit 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 sandbase-ai/hy-wu-edit.

{
  "prompt": "Using image 1 as the base image, replace the outfit with the clothing from image 2 while keeping the subject, pose, and background unchanged.",
  "aspect_ratio": "21:9",
  "output_format": "png"
}

Technical Specs

Specification	Details
Model ID	`sandbase-ai/hy-wu-edit`
Execution mode	`async`
Task type	`image`
`seed`	`integer` · optional
`images`	`array` · 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`
`output_format`	`string` · optional · choices: `jpeg`, `png`
`enable_thinking`	`boolean` · optional
`num_inference_steps`	`integer` · optional · min `1` · max `100`