FIBO Edit 1.5 Image Editing API
https://api.hiapi.ai /v1/tasks Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).
Model summary
| Model name | fibo-edit-1.5/image-to-image |
|---|---|
| Type | Image editing (image-to-image) |
| Endpoint | POST /v1/tasks |
| Pricing | See HiAPI Pricing |
FIBO Edit 1.5: Edit an image with one instruction, combine up to 4 reference images for compositing or try-ons, or use a mask to change one area.
Production guidance
- For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
- GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
- Result URLs expire — copy the output to your own storage once the task succeeds.
Best suited for
Combine a person with a garment, or a product with a scene, in one instruction.
image_urlsinstructionaspect_ratioUse a mask to change only the floor, background or one object.
mask_urlChange colors, seasons or mood while keeping structure and detail.
instructionRequest parameters
model string required Fixed value fibo-edit-1.5/image-to-image.
input object required Business parameters.
image_urls string[] required 1–4 public image URLs (http/https). Order matters: “image 1, image 2” in the instruction follow this order.
instruction string required The edit to make, including what to keep.
aspect_ratio enum optional Output ratio, applies only with 2 or more images. If omitted, follows the first image. With one image the output keeps that image’s ratio.
mask_url string optional Optional mask URL for single-image edits: white marks the area to change, black is kept; must match the image size.
seed integer optional Random seed; the same seed and inputs give the same result.
callback object optional Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.
url string required Required when callback is set; HTTPS URL that receives terminal task notifications.
when enum optional Callback trigger timing. Use final.
Example requests
The corduroy jacket from image 2 is put on the person in image 1 while pose, face and background stay the same.
{
"model": "fibo-edit-1.5/image-to-image",
"input": {
"image_urls": [
"https://dev-static.hiapi.ai/model-onboarding/fibo-edit-1.5/2026/10/16/1792150791858-9ed857b3db0a2f7c-i1-model.jpg",
"https://dev-static.hiapi.ai/model-onboarding/fibo-edit-1.5/2026/10/16/1792150835692-61b39dc0f55655a0-i2-jacket.jpg"
],
"instruction": "Dress the woman in image 1 with the mustard corduroy jacket from image 2, worn open over her white t-shirt. Keep her pose, face and the studio background.",
"aspect_ratio": "3:4"
}
}Getting the result
- The response returns a taskId immediately without waiting for generation to finish.
- In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
- When status=success, download the image from output[].url.
- When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.
FAQ
What edits can FIBO Edit 1.5 do?
Recolors, background swaps, season or style changes, local replacements, and combining several images, such as garment try-ons or placing a product in a scene.
How many images can I pass?
image_urls takes 1–4 images. Order matters: “image 1, image 2” in the instruction follow this order.
When does aspect_ratio apply?
Only with 2 or more images; if omitted it follows the first image. With one image the output keeps its ratio, and the online Playground shows the ratio option only after 2 or more uploads.
How do masks work?
mask_url is for single-image edits only. White is the area to change, black is kept, and the mask must match the image size.
What is the output format?
One PNG image per request, downloaded from output[].url.
Why do the same inputs give the same result?
seed defaults to 5555, so the same seed and inputs reproduce the result. Change the seed for a different one.
Which model should I use without a source image?
Use FIBO Gen 1.5 to generate from text.