Depth Anything Image API Documentation

Depth Anything Image API Documentation

Playground

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

Features

Depth Anything Image converts a single input image into a grayscale depth map for depth-conditioned generation, relighting, compositing, 2.5D effects, and 3D workflows.

The generated depth map preserves the input image resolution and represents relative scene depth, with nearby surfaces appearing lighter and distant surfaces appearing darker.

Why Choose This?

• Single-image depth estimation
  Generate a detailed depth map directly from one input image.

• Clear depth structure
  Preserve object boundaries and scene layering for downstream image and 3D workflows.

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

• Grayscale depth representation
  Nearby surfaces appear lighter, while distant surfaces appear darker.

• Multiple output formats
  Export the depth map as jpeg, png, or webp.

• Simple image workflow
  Provide an image URL, choose the output format, and generate the depth map.

Parameters

How to Use

1. Provide an input image — Upload an image or provide its URL.
2. Choose output format optional — Select jpeg, png, or webp.
3. Submit — Run the model to generate the grayscale depth map.
4. Use the result — Apply the depth map in generation, relighting, compositing, parallax, or 3D workflows.

Pricing

Pricing is fixed at $0.005 per image.

output_format does not add a separate charge.

Best Use Cases

• Depth-conditioned generation — Use depth maps in image-generation or ControlNet-style workflows.
• Relighting — Estimate scene depth to support depth-aware lighting adjustments.
• Depth of field — Create foreground and background separation for focus effects.
• Fog and atmospheric effects — Apply depth-dependent haze or environmental effects.
• Compositing — Use depth information to improve layering and spatial placement.
• 2.5D parallax — Create depth-based camera movement from a still image.
• 3D prototyping — Use relative depth as a starting point for displacement or scene reconstruction workflows.

Pro Tips

• Use png when you want to avoid lossy compression in downstream depth workflows.
• Use images with clear foreground and background separation for easier depth interpretation.
• Treat the result as relative depth, not real-world metric distance.
• Lighter areas represent surfaces estimated to be closer to the camera.
• Darker areas represent surfaces estimated to be farther from the camera.
• Use Depth Anything V3 Image when you need the newer image-depth workflow.

Notes

• image is required.
• output_format defaults to jpeg.
• Supported output formats are jpeg, png, and webp.
• Output resolution matches the input image resolution.
• The generated depth map represents relative rather than metric depth.
• Nearby surfaces appear lighter and distant surfaces appear darker.

Related Models

• Depth Anything Image — Generate grayscale depth maps from individual images.
• Depth Anything Video — Generate depth information from video input.
• Depth Anything V3 Image — Generate image depth maps with the newer Depth Anything V3 workflow.
• Depth Anything V3 Video — Generate depth maps from video using Depth Anything V3.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "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/image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters