Z Image Base API Documentation

Z Image Base API Documentation

Playground

Z-Image-Base is a 6 billion-parameter text-to-image model with full CFG support. Supports fine-tuning capabilities for maximum control over image generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Z-Image Base is a 6-billion parameter text-to-image model from Tongyi-MAI that generates photorealistic images with optional reference image guidance. Provide a text prompt alone, or add a reference image to guide the composition, style, or subject — all at an incredibly affordable price.

Why Choose This?

• Reference image guidance Optionally provide a reference image to influence the generated output’s composition, style, or subject matter.

• Flexible output sizing Customize width and height up to 1024px for any aspect ratio you need.

• Strength control Fine-tune how much the reference image influences the output with the strength parameter.

• Prompt Enhancer Built-in tool to automatically improve your prompts for better results.

• Ultra-affordable Just $0.01 per image — perfect for high-volume generation and experimentation.

Parameters

Strength Guide (with Reference Image)

• Lower values (0.2-0.4): Strong reference influence, output closely follows the reference image
• Medium values (0.5-0.7): Balanced blend of reference and prompt
• Higher values (0.8-1.0): Prompt dominates, reference serves as loose inspiration

How to Use

Text-to-Image (No Reference)

1. Write your prompt — describe the image you want to create.
2. Set dimensions — adjust width and height for your needs.
3. Run — submit and download your image.

With Reference Image

1. Upload a reference image — to guide the generation’s composition or style.
2. Write your prompt — describe the desired output.
3. Adjust strength — control how much the reference influences the result.
4. Run — submit and download your generated image.

Pricing

Best Use Cases

• Rapid Prototyping — Generate multiple concepts quickly at minimal cost.
• Style-guided Generation — Use reference images to maintain consistent aesthetics.
• Content Creation — Produce visuals for social media, blogs, and marketing.
• Creative Exploration — Experiment freely with different prompts and settings.
• Batch Generation — Create large volumes of images affordably.

Pro Tips

• Use the Prompt Enhancer to automatically improve your descriptions.
• For pure text-to-image, be specific about style, lighting, and composition.
• When using a reference image, start with strength around 0.6 and adjust based on results.
• Keep the same seed to iterate on a specific composition while tweaking the prompt.
• Lower strength values make output follow the reference more closely; higher values give the prompt more creative freedom.

Notes

• When no image is provided, the model runs in pure text-to-image mode.
• The strength parameter only applies when a reference image is provided.
• enable_sync_mode is only available through the API, not in the web interface.

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'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "1024*1024",
  "strength": 0.6,
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/z-image/base" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters