useknockout API reference

Base URL: https://useknockout--api.modal.run

`POST /remove`

Remove the background from an uploaded image.

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer <API_TOKEN>`
`Content-Type`	Auto	`multipart/form-data` (set by your client)

Body — multipart/form-data

Field	Type	Required	Description
`file`	binary	Yes	Image to process (JPEG, PNG, WebP). Max 25 MB.

Query params

Param	Type	Default	Description
`format`	string	`png`	`png` (default) or `webp`. Both include alpha.
`quality`	int	—	Compression quality 1–100 for `webp`. Ignored for `png` (lossless).
`max_dim`	int	—	Resize so the longest side is ≤ this many px (aspect preserved).
`width` / `height`	int	—	Exact resize. One alone preserves aspect; both set an exact box.
`despill`	float	—	Knockout Plus. Edge color decontamination strength `0`–`100`. Default behavior is full despill; lower to preserve original edge color.
`watermark`	string	—	Knockout Plus. Text watermark, bottom-right, auto-scaled.
`watermark_opacity`	float	`0.5`	Watermark opacity `0.0`–`1.0`.
`preset`	string	—	Knockout Plus. Apply a saved preset by name (see `/presets`). Explicit params override preset values.

Params marked Knockout Plus require a pro-tier key; other callers receive 402. quality, max_dim, width, height are available on all paid tiers.

Response — image/png or image/webp with a transparent background.

`POST /remove-url`

Fetch an image from a URL and remove its background.

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer <API_TOKEN>`
`Content-Type`	Yes	`application/json`

Body — JSON

{
  "url": "https://example.com/image.jpg",
  "format": "png"
}

Response — same as /remove.

`POST /psd`

Background removal exported as a layered Photoshop .psd — the cutout sits on its own transparent layer ("Cutout"), ready to edit in Photoshop, Affinity, or Photopea.

Paid endpoint. Billed as a $0.10/image add-on (its own meter, independent of your base per-image rate). Included free with Knockout Plus.

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer <API_TOKEN>` (paid tier)
`Content-Type`	Auto	`multipart/form-data`

Body — multipart/form-data

Field	Type	Default	Description
`file`	binary	—	Image to process. Max 25 MB.
`max_dim` / `width` / `height`	int	—	Resize the output (see `/remove`).
`despill`	float	—	Knockout Plus. Edge decontamination `0`–`100`.
`watermark`	string	—	Knockout Plus. Text watermark.
`preset`	string	—	Knockout Plus. Apply a saved preset.

Response — image/vnd.adobe.photoshop (a .psd with a transparent cutout layer).

`POST /replace-bg`

Remove the background and composite the subject onto a new background — solid color or a remote image.

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer <API_TOKEN>`
`Content-Type`	Auto	`multipart/form-data` (set by your client)

Body — multipart/form-data

Field	Type	Required	Description
`file`	binary	Yes	Foreground image to process. Max 25 MB.
`bg_color`	string	No (default `#FFFFFF`)	Hex color for the new background. Examples: `#000000`, `#ff5733`, `#1a73e8`.
`bg_url`	string	No	Remote URL of a background image. Takes precedence over `bg_color`.
`format`	string	No (default `png`)	Output format: `png`, `webp`, or `jpg` (smallest, opaque only).
`quality`	int	No	Compression quality 1–100 (`jpg`/`webp`).
`max_dim` / `width` / `height`	int	No	Resize the output (see `/remove`).
`despill`	float	No	Knockout Plus. Edge decontamination `0`–`100`.
`watermark` / `watermark_opacity`	string / float	No	Knockout Plus. Text watermark + opacity.
`preset`	string	No	Knockout Plus. Apply a saved preset.

Response — image/png, image/webp, or image/jpeg with the subject composited onto the new background. Edges are cleaned via closed-form foreground matting (no color spill, no halo).

`POST /remove-batch`

Remove backgrounds from up to 10 images in one call.

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer <API_TOKEN>`
`Content-Type`	Auto	`multipart/form-data`

Body — multipart/form-data with repeated files fields.

Query params

Param	Type	Default	Description
`format`	string	`png`	`png` or `webp`. Applies to every result.

Response — JSON:

{
  "count": 3,
  "format": "png",
  "results": [
    { "filename": "a.jpg", "success": true, "format": "png", "size_bytes": 124503, "data_base64": "..." },
    { "filename": "b.jpg", "success": true, "format": "png", "size_bytes": 98321, "data_base64": "..." },
    { "filename": "c.jpg", "success": false, "error": "Invalid or unsupported image" }
  ]
}

Each data_base64 decodes to PNG/WebP bytes with a transparent background.

`POST /remove-batch-url`

Same as /remove-batch but takes a JSON array of remote URLs.

Body — JSON:

{
  "urls": ["https://example.com/a.jpg", "https://example.com/b.jpg"],
  "format": "png"
}

Response — same JSON shape as /remove-batch, with url in place of filename.

`POST /mask`

Return just the black/white alpha mask as a grayscale PNG/WebP. Useful for chaining into your own compositing pipeline (Photoshop actions, ffmpeg keying, custom workflows).

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`format`	string	`png`	`png` or `webp`.

Response — grayscale image (0 = background, 255 = subject).

`POST /smart-crop`

Auto-crop to the subject's tight bounding box + padding.

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`padding`	int	`24`	Pixels of padding around the bbox.
`transparent`	bool	`true`	`true` → cropped cutout with transparent bg. `false` → cropped region from the original image (bg preserved).
`format`	string	`png`	`png`, `webp`, or `jpg` (when `transparent=false`).

Response — cropped image.

`POST /shadow`

Composite the subject onto a new background with a configurable drop shadow.

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`bg_color`	string	`#FFFFFF`	Hex color for the new background.
`bg_url`	string	—	Optional remote URL. Takes precedence over `bg_color`.
`shadow_color`	string	`#000000`	Hex color for the shadow.
`shadow_offset_x`	int	`8`	Shadow offset in pixels (X).
`shadow_offset_y`	int	`12`	Shadow offset in pixels (Y).
`shadow_blur`	int	`14`	Gaussian blur radius in pixels.
`shadow_opacity`	float	`0.45`	0.0–1.0.
`format`	string	`png`	`png`, `webp`, or `jpg`.

`POST /sticker`

Subject with a thick outline on a transparent background — iMessage / WhatsApp / Telegram sticker style.

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`stroke_color`	string	`#FFFFFF`	Outline color.
`stroke_width`	int	`20`	Outline width in pixels (capped at 80).
`format`	string	`png`	`png` or `webp`.

`POST /outline`

Subject on transparent background with a thin outline.

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`outline_color`	string	`#000000`	Outline color.
`outline_width`	int	`4`	Outline width in pixels (capped at 60).
`format`	string	`png`	`png` or `webp`.

`POST /silhouette` (v0.8.0)

Two-tone silhouette portrait — subject filled with one solid color, background with another. Apple Music / Spotify avatar style. Use for stylized profile pictures, podcast cover art, anonymized portraits, or branding placeholders.

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`subject_color`	string	`#7C3AED`	Fill color for the subject.
`bg_color`	string	`#FFFFFF`	Fill color for the background.
`format`	string	`png`	`png`, `webp`, or `jpg`.

`POST /inpaint` (v0.8.0)

LaMa-based image inpainting — remove objects, people, watermarks, or the subject itself and fill the hole with plausible background. Three modes, auto-detected:

mask field present → user-supplied mask (white = inpaint, black = keep)
x,y,w,h fields present → bbox mode (rectangular region)
Neither → auto-subject mode (BiRefNet derives the subject mask and inverts it — erases the subject, keeps the scene)

Field	Type	Default	Description
`file`	binary	required	Source image.
`mask`	binary	—	Grayscale mask image (white = inpaint). Resized to match `file` if needed.
`x` / `y` / `w` / `h`	int	—	Bbox mode: all four required together, must lie inside the image.
`dilation`	int	`8`	Expand the mask by N pixels (`0`–`32`) before inpainting. Higher values reduce ghost outlines from tight masks.
`format`	string	`png`	`png`, `webp`, or `jpg`.

Responses include x-knockout-mode (mask | bbox | auto-subject) and, when the mask covers more than half the image, an x-knockout-warning header (LaMa quality degrades on very large masks). Auto-subject mode returns 422 if no subject is detected.

`POST /studio-shot`

E-commerce preset: remove background → tight crop → center on solid-color canvas → optional drop shadow → standardized aspect ratio.

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`bg_color`	string	`#FFFFFF`	Canvas color.
`aspect`	string	`1:1`	`W:H` format. Examples: `1:1`, `4:5`, `16:9`, `3:2`.
`padding`	int	`48`	Padding around the subject in pixels.
`shadow`	bool	`true`	Include a soft drop shadow.
`transparent`	bool	`false`	Keep a transparent background. `bg_color` and `shadow` are ignored; output is forced to PNG.
`enhance`	bool	`false`	Off by default. Set `true` for a subtle brightness + saturation lift (ecommerce-ready). Leave off for true-to-life color.
`enhance_strength`	float	`0.15`	Lift amount, `0.0`–`0.5`. Only applies when `enhance=true`.
`format`	string	`jpg`	`png`, `webp`, or `jpg`.
`quality`	int	—	Compression quality 1–100 (`jpg`/`webp`).
`max_dim` / `width` / `height`	int	—	Resize the output (see `/remove`).
`despill`	float	—	Knockout Plus. Edge decontamination `0`–`100`.
`watermark` / `watermark_opacity`	string / float	—	Knockout Plus. Text watermark + opacity.
`preset`	string	—	Knockout Plus. Apply a saved preset.

`POST /collage`

Product collage: send 2–9 photos, each is background-removed and tight-cropped, then laid out around a main image on a solid canvas. Built for e-commerce hero images (main product + accessories).

Paid tiers only. Billed at N base-image units (each photo is a full model pass — 9 photos = 9 × your per-image price).

Field	Type	Default	Description
`files`	binary[]	required	2–9 images, sent as repeated `files` form fields.
`main_index`	int	`0`	Which image is the hero (0-based).
`main_position`	string	`BR`	Hero anchor: `TL`, `T`, `TR`, `L`, `C`, `R`, `BL`, `B`, `BR`. Hero takes ~65% of the canvas; the rest fill the remaining space in equal cells.
`bg_color`	string	`#FFFFFF`	Canvas color.
`aspect`	string	`1:1`	`W:H` canvas ratio (between `1:5` and `5:1`). Canvas is 1600px on the long side.
`padding`	int	`24`	Padding inside each cell (px, 0–200).
`format`	string	`jpg`	`png`, `webp`, or `jpg`.
`quality`	int	—	Compression quality 1–100 (`jpg`/`webp`).
`max_dim`	int	—	Cap the output's longest side (px).
`despill`	float	—	Knockout Plus. Edge decontamination `0`–`100`, applied to every cutout.
`watermark` / `watermark_opacity`	string / float	—	Knockout Plus. Text watermark + opacity.
`preset`	string	—	Knockout Plus. Apply a saved preset (`quality`, `max_dim`, `despill`, `watermark`).

curl -X POST "https://useknockout--api.modal.run/collage" \
  -H "Authorization: Bearer kno_..." \
  -F "files=@main-product.jpg" \
  -F "files=@accessory-1.jpg" \
  -F "files=@accessory-2.jpg" \
  -F "files=@accessory-3.jpg" \
  -F "main_position=BR" \
  -o collage.jpg

Use cases: marketplace hero images (product + accessories in one shot), listing thumbnails, bundle shots.

`POST /video/remove` · `GET /jobs/{job_id}` (v0.11.0)

Video background removal — frame-by-frame BiRefNet with temporal alpha smoothing, async. Submit a clip, get a job_id back immediately, poll for the result.

Paid tiers only. Billed at $0.10 per output second ($0.08 on Knockout Plus — a 10s clip = $1.00 / $0.80), charged on successful completion only. Billing is on output seconds, so speed=2 halves the cost.

Field	Type	Default	Description
`file`	binary	required	`mp4`, `mov`, `avi`, `webm`, or `mkv`. Max 15 seconds, 200MB. Frames above 1920px are downscaled for processing.
`format`	string	`prores4444`	`prores4444` — MOV with a real 10-bit alpha channel (drops into DaVinci Resolve, Premiere Pro, After Effects, Final Cut; no green screen). `webm` — VP9 with alpha, for web. `mp4` — H.264, requires an opaque background (no alpha).
`bg_color`	string	—	Composite every frame onto a solid hex color instead of transparency.
`bg_image`	binary	—	Composite every frame onto an uploaded backdrop image. Precedence: `bg_image` > `bg_blur` > `bg_color` > transparent.
`bg_blur`	int	`0`	`1`–`100`: composite onto a blurred copy of the source frame (portrait-mode look).
`speed`	float	`1.0`	`0.25`–`4.0` output speed multiplier. Audio is tempo-shifted to match.
`smoothing`	int	`30`	`0`–`100` temporal alpha smoothing across frames. Kills matte flicker; lower it for fast-moving subjects.

Processing runs at the source frame rate capped at 30fps. Audio is preserved.

# 1. Submit
curl -X POST "https://useknockout--api.modal.run/video/remove" \
  -H "Authorization: Bearer kno_..." \
  -F "file=@clip.mp4" \
  -F "format=prores4444"
# -> { "job_id": "…", "status": "queued", "seconds": 9.6, "poll": "/jobs/…" }

# 2. Poll until done
curl "https://useknockout--api.modal.run/jobs/JOB_ID" \
  -H "Authorization: Bearer kno_..."
# -> { "status": "done", "progress": 100, "result_url": "https://…" }  (URL valid 1h)

GET /jobs/{job_id} returns status (queued | processing | done | error), progress (0–100), and a signed result_url when done. Jobs are visible only to the key that created them.

Use cases: product videos for marketplace listings, talking-head cutouts, social clips on brand backgrounds, editor pipelines needing true alpha.

`POST /presets` · `GET /presets` · `DELETE /presets/{name}`

Knockout Plus. Save reusable output configs and apply them by name with preset=<name> on /remove, /replace-bg, /studio-shot, and /psd. A preset sets defaults; any explicit param on the request overrides it.

POST /presets — create/update. JSON body { "name": "web-thumb", "config": { "max_dim": 800, "quality": 75, "despill": 60, "watermark": "© Brand" } }. Config keys: quality, max_dim, width, height, despill, watermark (unknown keys dropped).
GET /presets — list your presets.
DELETE /presets/{name} — delete one.

Presets are per-user (tied to your API key's account). Requires a pro-tier key.

`POST /compare`

Before/after side-by-side preview — original on the left, transparent cutout (on a checkerboard) on the right. Great for marketing / social media screenshots.

Field	Type	Default	Description
`file`	binary	required	Foreground image.
`format`	string	`png`	`png` or `webp`.

`POST /headshot` (v0.4.0)

Studio-quality professional headshot — background removed, neutral studio backdrop, optional soft shadow, smart crop to bust framing. One call.

Field	Type	Default	Description
`file`	binary	required	Source portrait.
`bg_color`	string	`#f5f5f5`	Studio backdrop hex.
`add_shadow`	bool	`true`	Soft drop shadow.
`crop`	string	`bust`	`bust`, `head`, or `full`.
`format`	string	`png`	`png`, `webp`, or `jpg`.

`POST /preview` (v0.4.0)

Cheap, fast low-res preview — 512px max, watermark optional. Use for thumbnail UI before user pays for full-res. Returns in ~1.5s.

Field	Type	Default	Description
`file`	binary	required	Source image.
`max_size`	int	`512`	Max edge length.
`watermark`	bool	`false`	Add `useknockout` watermark.

`POST /estimate` (v0.4.0)

Returns expected processing time + output size without running the model. Use to show users "this'll take ~3s, ~1.2 MB" before they hit submit.

curl -X POST "https://useknockout--api.modal.run/estimate" \
  -H "Content-Type: application/json" \
  -d '{"width": 2048, "height": 1536, "endpoint": "remove"}'

Response: {"estimated_seconds": 2.4, "estimated_output_kb": 1180, "warm": true}

`GET /stats` (v0.4.0)

Public stats — total images processed, last-24h count, last-7d trend. Powered by Modal Dict cross-container counter. No auth required.

curl https://useknockout--api.modal.run/stats

`POST /upscale` (v0.6.0, backend default changed v0.9.0)

Real-ESRGAN / Swin2SR x2/x4 super-resolution. Takes blurry/small images, outputs 2x or 4x larger with AI-restored detail. Not pixel stretching — invents plausible texture.

v0.9.0 — default backend is Real-ESRGAN x4plus: restores and invents plausible detail, best "wow" on low-res or degraded photos, and faster (single pass, no tiling). Swin2SR (SwinV2 Transformer) remains available via model=swin2sr: faithful, no invented detail — prefer it for accuracy-sensitive product or archival work.

# default — Real-ESRGAN (best on low-res / degraded photos)
curl -X POST "https://useknockout--api.modal.run/upscale" \
  -H "Authorization: Bearer $KNOCKOUT_TOKEN" \
  -F "file=@small.jpg" \
  -F "scale=4" \
  -o upscaled.png

# Swin2SR (faithful — best for product / archival accuracy)
curl -X POST "https://useknockout--api.modal.run/upscale" \
  -H "Authorization: Bearer $KNOCKOUT_TOKEN" \
  -F "file=@product.jpg" \
  -F "scale=4" \
  -F "model=swin2sr" \
  -o upscaled.png

Field	Type	Default	Description
`file`	binary	required	Source image.
`scale`	int	`4`	`2` or `4`.
`model`	string	`realesrgan`	`realesrgan` (default) restores detail — best on low-res/degraded photos. `swin2sr` is faithful (no invented detail) for accuracy-sensitive work.
`face_enhance`	bool	`false`	Route through GFPGAN for facial detail. Implies Real-ESRGAN backend.
`format`	string	`png`	`png`, `webp`, or `jpg`.

Use cases: restore old photos, enlarge product shots, fix low-res screenshots, upscale AI-generated thumbnails.

`POST /face-restore` (v0.5.0)

GFPGAN v1.4 face restoration. Detects faces, restores blurred/compressed/damaged ones while preserving identity. Background also upscaled via Real-ESRGAN. Multi-face safe.

curl -X POST "https://useknockout--api.modal.run/face-restore" \
  -H "Authorization: Bearer $KNOCKOUT_TOKEN" \
  -F "file=@blurry-portrait.jpg" \
  -o restored.png

Field	Type	Default	Description
`file`	binary	required	Source image with one or more faces.
`format`	string	`png`	`png`, `webp`, or `jpg`.

Use cases: old family photos, Zoom screenshots, dating app pics, restore CCTV stills.

`POST /colorize` (v0.8.0)

DDColor colorization for black-and-white or grayscale photos. ConvNeXt-Large backbone predicts color in LAB space — single feed-forward pass, ~500ms warm. Color inputs are accepted too (treated as grayscale internally).

curl -X POST "https://useknockout--api.modal.run/colorize" \
  -H "Authorization: Bearer $KNOCKOUT_TOKEN" \
  -F "file=@bw-photo.jpg" \
  -o colorized.png

Field	Type	Default	Description
`file`	binary	required	Source image.
`format`	string	`png`	`png`, `webp`, or `jpg`.

Use cases: restore old family photos, colorize archival/historical images, stylize scans.

`GET /health`

Returns {"status":"ok","model":"ZhengPeng7/BiRefNet"}. No auth required.

`GET /docs`

Interactive OpenAPI (Swagger) UI.

Errors

Code	Meaning
`400`	Invalid image, missing field, malformed URL, invalid hex color, or batch > 10 items
`401`	Missing `Authorization` header
`402`	Tier limit: free tier hitting a paid endpoint, free monthly quota (10) exhausted, non-Plus key using a Plus param, or demo key limits
`403`	Invalid bearer token
`404`	Unknown `job_id` on `GET /jobs/{job_id}`
`413`	Image exceeds 25 MB limit (200 MB for video)
`422`	`/inpaint` auto-subject mode found no subject
`500`	Server error (check dashboard logs)

Edge quality

All endpoints apply closed-form foreground matting (via pymatting) after mask prediction. This estimates pure foreground color at soft edges, eliminating color spill from the original background. Result: no halos, no fringing, even on backgrounds that differ sharply from the subject.

Client examples

Python

import os
import requests

URL = "https://useknockout--api.modal.run/remove"
TOKEN = os.environ["KNOCKOUT_TOKEN"]  # get yours at useknockout.com/signin

with open("input.jpg", "rb") as f:
    resp = requests.post(
        URL,
        headers={"Authorization": f"Bearer {TOKEN}"},
        files={"file": f},
    )
resp.raise_for_status()

with open("output.png", "wb") as f:
    f.write(resp.content)

Node.js SDK (recommended)

npm i @useknockout/node

import { writeFile } from "node:fs/promises";
import { Knockout } from "@useknockout/node";

const client = new Knockout({ token: process.env.KNOCKOUT_TOKEN! });

// 1. Remove background → transparent PNG
const png = await client.remove({ file: "./input.jpg" });
await writeFile("out.png", png);

// 2. Replace background with a color
const jpg = await client.replaceBackground({
  file: "./input.jpg",
  bgColor: "#FF5733",
  format: "jpg",
});
await writeFile("out.jpg", jpg);

// 3. Replace background with a remote image
const composed = await client.replaceBackground({
  file: "./input.jpg",
  bgUrl: "https://example.com/mountains.jpg",
});

// 4. Batch — process 10 URLs in one call
const batch = await client.removeBatchUrl({
  urls: ["https://example.com/a.jpg", "https://example.com/b.jpg"],
});
for (const r of batch.results) {
  if (r.success) await writeFile(`out-${r.url}.png`, Buffer.from(r.data_base64!, "base64"));
}

Node.js (raw fetch, no SDK)

import { readFile, writeFile } from "node:fs/promises";

const URL = "https://useknockout--api.modal.run/remove";
const TOKEN = process.env.KNOCKOUT_TOKEN;

const buf = await readFile("input.jpg");
const form = new FormData();
form.set("file", new Blob([buf]), "input.jpg");

const res = await fetch(URL, {
  method: "POST",
  headers: { Authorization: `Bearer ${TOKEN}` },
  body: form,
});
if (!res.ok) throw new Error(await res.text());

await writeFile("output.png", Buffer.from(await res.arrayBuffer()));

TypeScript (browser / Next.js)

export async function removeBackground(file: File, token: string) {
  const form = new FormData();
  form.append("file", file);

  const res = await fetch("https://useknockout--api.modal.run/remove", {
    method: "POST",
    headers: { Authorization: `Bearer ${token}` },
    body: form,
  });

  if (!res.ok) throw new Error(`knockout error: ${res.status}`);
  return await res.blob(); // PNG with alpha
}

Go

package main

import (
    "bytes"
    "io"
    "mime/multipart"
    "net/http"
    "os"
)

func removeBG(path, token string) ([]byte, error) {
    f, err := os.Open(path)
    if err != nil { return nil, err }
    defer f.Close()

    body := &bytes.Buffer{}
    w := multipart.NewWriter(body)
    part, _ := w.CreateFormFile("file", path)
    io.Copy(part, f)
    w.Close()

    req, _ := http.NewRequest("POST",
        "https://useknockout--api.modal.run/remove", body)
    req.Header.Set("Authorization", "Bearer "+token)
    req.Header.Set("Content-Type", w.FormDataContentType())

    resp, err := http.DefaultClient.Do(req)
    if err != nil { return nil, err }
    defer resp.Body.Close()
    return io.ReadAll(resp.Body)
}

cURL — WebP output (smaller files)

curl -X POST "https://useknockout--api.modal.run/remove?format=webp" \
  -H "Authorization: Bearer $TOKEN" \
  -F "file=@input.jpg" \
  -o output.webp

Uh oh!

FilesExpand file tree

APIREFERENCE.md

Latest commit

History

APIREFERENCE.md

File metadata and controls

useknockout API reference

POST /remove

POST /remove-url

POST /psd

POST /replace-bg

POST /remove-batch

POST /remove-batch-url

POST /mask

POST /smart-crop

POST /shadow

POST /sticker

POST /outline

POST /silhouette (v0.8.0)

POST /inpaint (v0.8.0)

POST /studio-shot

POST /collage

POST /video/remove · GET /jobs/{job_id} (v0.11.0)

POST /presets · GET /presets · DELETE /presets/{name}

POST /compare

POST /headshot (v0.4.0)

POST /preview (v0.4.0)

POST /estimate (v0.4.0)

GET /stats (v0.4.0)

POST /upscale (v0.6.0, backend default changed v0.9.0)

POST /face-restore (v0.5.0)

POST /colorize (v0.8.0)

GET /health

GET /docs

Errors

Edge quality

Client examples

Python

Node.js SDK (recommended)

Node.js (raw fetch, no SDK)

TypeScript (browser / Next.js)

Go

cURL — WebP output (smaller files)

`POST /remove`

`POST /remove-url`

`POST /psd`

`POST /replace-bg`

`POST /remove-batch`

`POST /remove-batch-url`

`POST /mask`

`POST /smart-crop`

`POST /shadow`

`POST /sticker`

`POST /outline`

`POST /silhouette` (v0.8.0)

`POST /inpaint` (v0.8.0)

`POST /studio-shot`

`POST /collage`

`POST /video/remove` · `GET /jobs/{job_id}` (v0.11.0)

`POST /presets` · `GET /presets` · `DELETE /presets/{name}`

`POST /compare`

`POST /headshot` (v0.4.0)

`POST /preview` (v0.4.0)

`POST /estimate` (v0.4.0)

`GET /stats` (v0.4.0)

`POST /upscale` (v0.6.0, backend default changed v0.9.0)

`POST /face-restore` (v0.5.0)

`POST /colorize` (v0.8.0)

`GET /health`

`GET /docs`