Seedance 2.5 Now Live | Try in Video Generator →

wavespeed-ai/

Phota Edit transforms existing images using natural language instructions. Supports up to 10 reference images, 1K and 4K resolutions, and batch output up to 4 images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-image
Input

Idle

Change the man's clothes in the picture to beach casual wear and put on sunglasses.

$0.09per run·~11 / $1

Next:

ExamplesView all

Change the man's clothes in the picture to beach casual wear and put on sunglasses.

Change the man's clothes in the picture to beach casual wear and put on sunglasses.

Related Models

README

Phota Edit

Phota Edit is an AI-powered image editing model that transforms photos using natural language instructions. Describe the change you want — swap clothing, alter backgrounds, adjust styles, add or remove objects — and the model applies precise, context-aware edits while preserving the rest of the image. Supports multiple input images, batch output, and flexible aspect ratio control.

Why Choose This?

  • Natural-language editing Describe your edit in plain text — no masks, no manual selections, no technical knowledge required.

  • Multi-image input Upload multiple reference images to provide richer visual context for complex edits.

  • 4K output support Generate high-resolution edited results for print, production, or archival use.

  • Flexible aspect ratio control Output in auto, 1:1, 16:9, 4:3, 3:4, or 9:16 to match your target platform.

  • Multiple output formats Export in JPEG, PNG, or WebP for any downstream workflow.

  • Batch output Generate multiple edited variations in a single run using the num_images parameter.

Parameters

ParameterRequiredDescription
promptYesText description of the desired edit.
imagesNoOne or more source images to edit (URL or file upload). Click Add Item for more.
resolutionNoOutput resolution: 1K (default) or 4K.
num_imagesNoNumber of edited output variations to generate per run. Default: 1.
aspect_ratioNoOutput aspect ratio: auto (default), 1:1, 16:9, 4:3, 3:4, 9:16.
output_formatNoOutput file format: jpeg (default), png, or webp.

How to Use

  1. Write your prompt — describe exactly what should change in the image (e.g., "Change the man's clothes to beach casual wear and put on sunglasses.").
  2. Upload your image(s) — provide one or more source images via URL or drag-and-drop. Click Add Item to add more.
  3. Select resolution — 1K for standard output, 4K for high-resolution results.
  4. Set num_images (optional) — generate multiple variations in one run.
  5. Choose aspect ratio — use auto to preserve the source ratio, or select a specific format.
  6. Choose output format — jpeg, png, or webp based on your delivery needs.
  7. Submit — generate and download your edited image.

Pricing

ResolutionCost per Image
1K$0.09
4K$0.18

Billing Rules

  • 1K: $0.09 per image
  • 4K: $0.18 per image (2× base price)
  • Total cost = cost per image × num_images

Best Use Cases

  • Fashion & Apparel — Swap clothing, accessories, or outfit styles on model photos without reshooting.
  • E-commerce — Edit product images to showcase different colors, settings, or variants from a single source.
  • Marketing & Advertising — Update visual assets quickly — change backgrounds, props, or styling to match campaign needs.
  • Portrait Retouching — Make targeted appearance changes while preserving the overall look and feel.
  • Creative Concepting — Rapidly iterate on visual ideas and styling directions for client review.

Pro Tips

  • Be specific and descriptive in your prompt — the more detail you provide, the more accurate the edit.
  • Upload multiple images when you want the model to reference additional context, such as a target style or specific elements.
  • Use 4K output for final production assets and 1K for rapid iteration and testing.
  • Use PNG output for lossless results when editing images with text, graphics, or sharp edges.
  • Enable sync mode in API workflows where you need the result returned directly without polling.

Notes

  • Only prompt is required; all other parameters are optional.
  • Ensure image URLs are publicly accessible if using links rather than direct uploads.
  • Please ensure your content complies with WaveSpeed AI's usage policies.

Related Models

  • Phota Enhance — Restore and upscale images without editing using AI-powered detail reconstruction.
Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Phota Edit API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/phota/edit with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Phota Edit below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "resolution": "1K",
    "num_images": 1,
    "aspect_ratio": "auto",
    "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/phota/edit" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/phota/edit";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "resolution": "1K",
        "num_images": 1,
        "aspect_ratio": "auto",
        "output_format": "jpeg"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "resolution": "1K",
    "num_images": 1,
    "aspect_ratio": "auto",
    "output_format": "jpeg"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/phota/edit", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Phota Edit API — Frequently asked questions

What is the Phota Edit API?

Phota Edit is a WaveSpeedAI model for image editing, exposed as a REST API on WaveSpeedAI. Phota Edit transforms existing images using natural language instructions. Supports up to 10 reference images, 1K and 4K resolutions, and batch output up to 4 images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Phota Edit API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/phota-edit.

How much does Phota Edit cost per run?

Phota Edit starts at $0.090 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Phota Edit accept?

Key inputs: `prompt`, `images`, `aspect_ratio`, `resolution`, `enable_base64_output`, `enable_sync_mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/phota-edit.

How long does Phota Edit take to generate?

Median end-to-end generation time on WaveSpeedAI is around 50 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Phota Edit outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Phota Edit | Fast Image Editing API on WaveSpeedAI