GPT Image 2.5 is LIVE — Flare & Sunburst | Try in Image Generator →

wavespeed-ai/

Depth Anything V3 Image estimates a sharp, detailed depth map from a single image, ready for depth-conditioned generation, relighting, 3D and compositing workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-image
Input
Enable Safety Checker

Idle

$0.005per run·~200 / $1

Next:

ExamplesView all

Related Models

README

Depth Anything V3 Image

Depth Anything V3 Image estimates a detailed depth map from a single image using Depth Anything V3. It captures fine scene structure and object boundaries, handles sky regions more cleanly, and returns the depth map at the input image resolution.

Use grayscale output for depth-conditioned generation and compositing workflows, or choose inferno or turbo when you want a colorized depth visualization.

Why Choose This?

  • Detailed depth estimation
    Capture fine structures such as hair, foliage, thin objects, edges, and architectural details.

  • Sky-aware depth handling
    Place sky regions at the far end of the depth range instead of producing noisy depth values.

  • Control-workflow ready
    Use the default grayscale output directly in depth-conditioned generation and ControlNet-style pipelines.

  • Multiple colormaps
    Choose grayscale for depth workflows or inferno and turbo for visualized depth maps.

  • Input-resolution output
    The generated depth map matches the resolution of the source image.

  • Broad image support
    Works with photos, renders, illustrations, indoor scenes, and outdoor scenes.

Parameters

ParameterRequiredDescription
imageYesInput image provided as a URL or upload.
colormapNoDepth-map visualization: grayscale, inferno, or turbo. Default: grayscale. In grayscale mode, near surfaces are white and far surfaces are black.
output_formatNoOutput image format: jpeg, png, or webp. Default: jpeg.

How to Use

  1. Provide an input image — Upload an image or provide its URL.
  2. Choose a colormap optional — Use grayscale for generation and compositing workflows, or inferno / turbo for color visualization.
  3. Choose output format optional — Select jpeg, png, or webp.
  4. Submit — Generate and retrieve the depth map.

Pricing

Pricing is fixed at $0.005 per image.

OutputCost
One generated depth map$0.005

colormap and output_format do not add separate charges.

Best Use Cases

  • Depth-conditioned generation — Preserve the composition of a reference image while changing its content or visual style.
  • ControlNet-style workflows — Use grayscale depth as structural guidance for downstream generation.
  • Relighting — Use scene depth to support depth-aware lighting workflows.
  • Depth of field — Create foreground and background separation for portrait blur and focus effects.
  • Fog and atmospheric effects — Apply depth-based haze or environmental effects.
  • 2.5D parallax — Use the depth map as a displacement source for parallax animation.
  • 3D-aware editing — Use estimated scene depth for spatial edits and prototyping.
  • Compositing — Create depth-based masks and layered scene effects.

Pro Tips

  • Use grayscale when the depth map will be passed into another model or compositing workflow.
  • Use png when you want to avoid lossy compression in downstream depth processing.
  • Use inferno or turbo when the depth map is primarily for visualization.
  • In grayscale mode, white represents surfaces closer to the camera and black represents surfaces farther away.
  • Treat the result as relative depth, not real-world metric distance.
  • Use images with clear scene structure when you want easier foreground and background separation.

Notes

  • image is required.
  • colormap defaults to grayscale.
  • Supported colormaps are grayscale, inferno, and turbo.
  • output_format defaults to jpeg.
  • Supported output formats are jpeg, png, and webp.
  • Output resolution matches the input image resolution.
  • Depth is relative rather than metric.
  • In grayscale mode, near surfaces are white and far surfaces are black.

Related Models

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.

Depth Anything v3 Image API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/depth-anything-v3/image 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 Depth Anything v3 Image below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "colormap": "grayscale",
    "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/depth-anything-v3/image" \
  -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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"

# 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' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/depth-anything-v3/image";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
        "colormap": "grayscale",
        "output_format": "jpeg"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  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 = {
    "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
    "colormap": "grayscale",
    "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/depth-anything-v3/image", 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 = 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", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Depth Anything v3 Image API — Frequently asked questions

What is the Depth Anything v3 Image API?

Depth Anything v3 Image is a WaveSpeedAI model for image editing, exposed as a REST API on WaveSpeedAI. Depth Anything V3 Image estimates a sharp, detailed depth map from a single image, ready for depth-conditioned generation, relighting, 3D and compositing workflows. 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 Depth Anything v3 Image 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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/depth-anything-v3-image.

How much does Depth Anything v3 Image cost per run?

Depth Anything v3 Image starts at $0.005 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 Depth Anything v3 Image accept?

Key inputs: `image`, `colormap`, `enable_base64_output`, `enable_sync_mode`, `output_format`. 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/depth-anything-v3-image.

How do I get started with the Depth Anything v3 Image API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Depth Anything v3 Image outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.