Seedream 5.0 Pro уже здесь | Попробуйте в Генераторе изображений →
Войти

Z Image Turbo Inpaint | Fast Image Editing

wavespeed-ai/

Z-Image Turbo Inpaint delivers ultra-fast image inpainting with natural-language instructions—seamlessly fill, fix, or replace regions in your images with production-quality results. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

image-to-image
Ввод

Ожидание

A handsome anime-style man in his early 30s with medium-length wavy chestnut brown hair, slightly tousled with natural volume, and a well-groomed short beard. He sits in a warm-lit café interior, facing the camera with a gentle, relaxed smile and kind eyes. His eyes are large and expressive in classic anime style, with warm brown irises and soft highlights. He wears a dark olive-green casual jacket over a dark inner shirt, with the collar slightly open. The background shows a cozy café atmosphere with blurred warm wooden furniture, soft ambient lighting, and hints of windows casting golden light. The lighting is soft and warm, coming from the upper left, creating gentle shadows on the right side of his face. The art style is high-quality Japanese anime illustration with clean line art, smooth cel-shading, and warm color palette. The composition is a close-up portrait from chest up, with shallow depth of field. Makoto Shinkai cinematic style, detailed anime illustration, 4K quality.

$0.02за запуск·~50 / $1

Далее:

ПримерыСмотреть всё

A handsome anime-style man in his early 30s with medium-length wavy chestnut brown hair, slightly tousled with natural volume, and a well-groomed short beard. He sits in a warm-lit café interior, facing the camera with a gentle, relaxed smile and kind eyes. His eyes are large and expressive in classic anime style, with warm brown irises and soft highlights. He wears a dark olive-green casual jacket over a dark inner shirt, with the collar slightly open. The background shows a cozy café atmosphere with blurred warm wooden furniture, soft ambient lighting, and hints of windows casting golden light. The lighting is soft and warm, coming from the upper left, creating gentle shadows on the right side of his face. The art style is high-quality Japanese anime illustration with clean line art, smooth cel-shading, and warm color palette. The composition is a close-up portrait from chest up, with shallow depth of field. Makoto Shinkai cinematic style, detailed anime illustration, 4K quality.

A handsome anime-style man in his early 30s with medium-length wavy chestnut brown hair, slightly tousled with natural volume, and a well-groomed short beard. He sits in a warm-lit café interior, facing the camera with a gentle, relaxed smile and kind eyes. His eyes are large and expressive in classic anime style, with warm brown irises and soft highlights. He wears a dark olive-green casual jacket over a dark inner shirt, with the collar slightly open. The background shows a cozy café atmosphere with blurred warm wooden furniture, soft ambient lighting, and hints of windows casting golden light. The lighting is soft and warm, coming from the upper left, creating gentle shadows on the right side of his face. The art style is high-quality Japanese anime illustration with clean line art, smooth cel-shading, and warm color palette. The composition is a close-up portrait from chest up, with shallow depth of field. Makoto Shinkai cinematic style, detailed anime illustration, 4K quality.

Похожие модели

README

Z-Image Turbo Inpaint

Z-Image Turbo Inpaint is a fast, production-ready inpainting model for removing, repairing, or replacing specific regions in an image using simple natural-language instructions. Provide an image plus a mask, describe what you want to happen, and the model blends the edited region naturally into the original scene—optimized for low latency and clean results.

Where Z-Image Turbo Inpaint shines

  • Product photo cleanup (remove dust, labels, reflections, minor defects)
  • Object removal and background repair
  • Photo restoration and localized fixes
  • High-throughput pipelines that need consistent, quick turnaround

Key benefits

  • Natural, seamless blending Reconstructs masked regions with realistic texture, lighting, and structure to minimize visible seams.

  • Prompt-driven control Use plain English to specify what to remove or what should replace the masked area.

  • Fast iteration at scale Built for rapid reruns—ideal for design iteration, batch processing, and automation.

  • Simple API integration Straightforward inputs (image, mask, prompt) with stable behavior and no cold starts.

How it works

  1. Provide an input image.
  2. Provide a mask that marks the region to modify (the masked area is what the model will change).
  3. Provide a prompt describing the intended edit.
  4. The model fills or replaces the masked region while keeping the rest of the image stable.

Pricing

  • $0.02 per inpainted image

Tips for best results

  • Mask only what you need, then expand slightly if artifacts remain.
  • Use clean mask edges for structured objects; use softer/feathered edges for textures like hair, smoke, or fabric.
  • Be specific in the prompt when replacing content (object type, material, lighting, style).

More Image Tools on WaveSpeedAI

  • FLUX.2 [max] Edit — Production-grade AI image editing with natural-language instructions and precise control for high-fidelity commercial creative workflows.

  • FLUX.2 [flex] Edit — Fast, controllable AI image editing for clean inpainting, color-accurate adjustments, and consistent style preservation at scale.

  • Qwen Edit Plus — Prompt-driven AI inpainting and local image edits with strong composition preservation, ideal for background cleanup and targeted refinements.

Примечание:Этот сайт использует модели ИИ, предоставляемые третьими лицами.

Z Image Turbo Inpaint API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/z-image/turbo-inpaint 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 Z Image Turbo Inpaint 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",
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "mask_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/z-image/turbo-inpaint" \
  -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/z-image/turbo-inpaint";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "mask_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "mask_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}

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/z-image/turbo-inpaint", 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)

Z Image Turbo Inpaint API — Frequently asked questions

What is the Z Image Turbo Inpaint API?

Z Image Turbo Inpaint is a WaveSpeedAI model for image editing, exposed as a REST API on WaveSpeedAI. Z-Image Turbo Inpaint delivers ultra-fast image inpainting with natural-language instructions—seamlessly fill, fix, or replace regions in your images with production-quality results. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Z Image Turbo Inpaint 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/z-image-turbo-inpaint.

How much does Z Image Turbo Inpaint cost per run?

Z Image Turbo Inpaint starts at $0.020 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 Z Image Turbo Inpaint accept?

Key inputs: `prompt`, `image`, `mask_image`. 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/z-image-turbo-inpaint.

How long does Z Image Turbo Inpaint take to generate?

Median end-to-end generation time on WaveSpeedAI is around 5 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 Z Image Turbo Inpaint 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.

Z Image Turbo Inpaint | Fast Image Editing API on WaveSpeedAI