Seedream 5.0 Pro đã ra mắt | Thử trong Trình tạo ảnh →

Flux Fill Dev

wavespeed-ai /

FLUX.1 Fill [dev] is a 12B-parameter rectified flow transformer for text-guided image inpainting that fills areas of existing images from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-image
Đầu vào

Chờ

A white translucent silk scarf is wrapped around the neck and flutters in the wind.

$0.035cho mỗi lần chạy·~28 / $1

Tiếp theo:

Ví dụXem tất cả

A white translucent silk scarf is wrapped around the neck and flutters in the wind.

A white translucent silk scarf is wrapped around the neck and flutters in the wind.

White rustic star necklace

White rustic star necklace

A big colorful toy ball

A big colorful toy ball

blue triangular scarf with texture

blue triangular scarf with texture

place a cute little cat, sleeping on the sofa

place a cute little cat, sleeping on the sofa

Change the color to light pink clothes

Change the color to light pink clothes

Black lady's belt

Black lady's belt

Mô hình liên quan

README

FLUX Fill Dev

FLUX Fill Dev is a powerful AI-powered inpainting model that fills in masked regions of images based on text prompts. Upload an image and mask, describe what should appear in the masked area, and the model seamlessly generates new content that blends naturally with the surrounding image.

Why It Stands Out

  • Precise inpainting: Generate new content only in masked regions while preserving the rest.
  • Prompt-guided generation: Describe exactly what should appear in the masked area.
  • Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
  • LoRA support: Apply up to 3 custom LoRA models for specific styles.
  • Flexible resolution: Width and height adjustable from 256 to 1536 pixels.
  • Batch generation: Create multiple variations in a single request.
  • Reproducibility: Use the seed parameter to recreate exact results.

Parameters

ParameterRequiredDescription
imageYesSource image to edit (upload or public URL).
mask_imageYesMask image (white = generate, black = preserve).
promptYesText description of what to generate in the masked area.
widthNoOutput width: 256–1536 pixels (default: 1024).
heightNoOutput height: 256–1536 pixels (default: 1024).
num_inference_stepsNoQuality/speed trade-off (default: 28).
seedNoSet for reproducibility (default: 0).
guidance_scaleNoPrompt adherence strength (default: 30).
num_imagesNoNumber of images to generate (default: 1).
lorasNoLoRA models to apply. Up to 3 LoRAs.

How to Use

  1. Upload your source image — drag and drop a file or paste a public URL.
  2. Upload or create a mask image — white areas will be regenerated, black areas preserved.
  3. Write a prompt describing what should appear in the masked region. Use the Prompt Enhancer for AI-assisted optimization.
  4. Add LoRAs (optional) — apply up to 3 custom style LoRAs.
  5. Adjust parameters (optional) — set dimensions, guidance scale, and num_images.
  6. Click Run and download your edited image.

Best Use Cases

  • Object Replacement — Replace objects in images with new ones.
  • Background Editing — Change or extend backgrounds seamlessly.
  • Content Addition — Add new elements like clothing, accessories, or objects.
  • Photo Repair — Remove unwanted elements and fill with appropriate content.
  • Creative Compositing — Blend new elements into existing scenes naturally.

Pricing

OutputPrice
Per image$0.035

Pro Tips for Best Quality

  • Create clean, precise masks — white for areas to regenerate, black for areas to keep.
  • Be specific in your prompt about what should appear in the masked area.
  • Use higher guidance scale (25–35) for stronger prompt adherence.
  • Generate multiple images (num_images > 1) to explore variations.
  • Use LoRAs to apply consistent styles across multiple inpainting jobs.
  • Ensure mask edges are smooth for better blending results.

Notes

  • Maximum of 3 LoRAs per generation.
  • Width and height must be between 256 and 1536 pixels.
  • Ensure uploaded image URLs are publicly accessible.
  • Processing time varies based on resolution and current queue load.
  • Please ensure your content complies with usage guidelines.
Lưu ý:Trang web này sử dụng các mô hình AI do bên thứ ba cung cấp.

Flux Fill Dev API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-fill-dev 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 Flux Fill Dev 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",
    "size": "1024*1024",
    "num_inference_steps": 28,
    "seed": 0,
    "guidance_scale": 30,
    "num_images": 1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-fill-dev" \
  -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/flux-fill-dev";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "mask_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "size": "1024*1024",
        "num_inference_steps": 28,
        "seed": 0,
        "guidance_scale": 30,
        "num_images": 1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "size": "1024*1024",
    "num_inference_steps": 28,
    "seed": 0,
    "guidance_scale": 30,
    "num_images": 1
}

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/flux-fill-dev", 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)

Flux Fill Dev API — Frequently asked questions

What is the Flux Fill Dev API?

Flux Fill Dev is a WaveSpeedAI model for image editing, exposed as a REST API on WaveSpeedAI. FLUX.1 Fill [dev] is a 12B-parameter rectified flow transformer for text-guided image inpainting that fills areas of existing images from text prompts. 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 Flux Fill Dev 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/flux-fill-dev.

How much does Flux Fill Dev cost per run?

Flux Fill Dev starts at $0.035 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 Flux Fill Dev accept?

Key inputs: `prompt`, `image`, `size`, `seed`, `guidance_scale`, `num_inference_steps`. 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/flux-fill-dev.

How long does Flux Fill Dev take to generate?

Median end-to-end generation time on WaveSpeedAI is around 21 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 Flux Fill Dev 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.