Meta Muse Image Edit API Documentation
Playground
Try it on WaveSpeedAI!Meta Muse Image Edit transforms input images with text prompts, supporting prompt-guided image editing, visual refinements, creative variations, marketing assets, social content, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Meta Muse Image Edit edits one or more input images using natural-language instructions. Upload reference images, describe the transformation you want, choose an aspect ratio and output format, and generate the edited result.
Why Choose This?
-
Prompt-guided image editing
Edit images with simple natural-language instructions. -
Multi-image input support
Upload one or more reference images to guide the edit. -
Flexible aspect ratio
Choose the output aspect ratio based on your target layout. -
Multiple output formats
Select the image format that fits your workflow. -
Low-cost editing workflow
Generate edited images at a fixed price per run.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text instruction describing the desired edit or transformation. |
| image_urls | Yes | Input image URLs to edit. Supports up to 10 images. |
| aspect_ratio | No | Aspect ratio of the generated image. Leave empty to use the default or closest supported layout. |
| output_format | No | Output image format. For example: webp. |
How to Use
- Upload images — Provide one or more input images to edit.
- Write your prompt — Describe what should change and what should remain consistent.
- Choose aspect ratio optional — Select the layout that matches your target format.
- Choose output format — Select the image format for the edited result.
- Submit — Generate the edited image and retrieve the output URL.
Pricing
Pricing is fixed at $0.011 per run.
| Output | Cost |
|---|---|
| One edit run | $0.011 |
Best Use Cases
- Prompt-guided image editing — Transform an existing image with text instructions.
- Creative variations — Generate new versions of an image while keeping the main subject or composition.
- Marketing visuals — Update campaign images, social assets, thumbnails, or product visuals.
- Style changes — Adjust mood, lighting, scene style, or visual direction.
- Multi-reference edits — Use multiple images to guide composition, subject, or style.
Pro Tips
- Use clear prompts that describe both what should change and what should stay the same.
- Upload clean, high-quality reference images for better edit results.
- Use multiple images when identity, style, product details, or composition consistency matters.
- Keep the prompt focused on the desired transformation.
- Choose the aspect ratio based on the final use case.
- Use
webpwhen you want compact web-friendly output.
Related Models
- Meta Muse Image Text-to-Image — Generate images from natural-language prompts.
- Meta Muse Image Edit — Edit images with text instructions.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"image_urls": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "21:9",
"output_format": "webp"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/meta/muse-image/edit" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Describe the image to generate or the edit to apply. | |
| image_urls | array<string> | Yes | - | 1 ~ 10 items | Upload 1 to 10 reference images. |
| aspect_ratio | string | No | - | 21:9, 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, 9:16, 9:21 | - |
| output_format | string | No | webp | webp, png, jpeg | - |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |