Firered Image V1.1 Edit API Documentation

Firered Image V1.1 Edit API Documentation

Playground

FireRed Image Edit V1.1 enables precise image editing with natural-language instructions, supporting both English and Chinese prompts with multi-image references. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

FireRed Image V1.1 Edit is a powerful multi-image editing model that transforms reference images based on text prompts. Upload up to 3 reference images and describe the desired output — the model generates new images that combine elements, styles, or characters from your references with cinematic quality and retro aesthetics.

Why Choose This?

• Multi-image reference Combine elements from up to 3 reference images into a single cohesive output.

• Style-aware editing Excels at editorial looks, film grain, retro tones, and cinematic aesthetics.

• Flexible sizing Choose preset aspect ratios or custom dimensions — leave empty to preserve original proportions.

• Character consistency Maintain subject identity while transforming style, setting, or mood.

• Prompt Enhancer Built-in tool to automatically improve your descriptions.

Parameters

How to Use

1. Upload reference images — add up to 3 images for style, character, or scene guidance.
2. Write your prompt — describe the desired output with style and mood details.
3. Set size (optional) — choose a preset ratio, custom dimensions, or leave empty to keep original proportions.
4. Use Prompt Enhancer (optional) — click to refine your description.
5. Run — submit and download your edited image.

Pricing

Best Use Cases

• Editorial Portraits — Create stylized portraits with film grain and retro aesthetics.
• Character Styling — Transform subjects into different settings, eras, or moods.
• Vintage Looks — Generate images with warm retro tones and classic Americana vibes.
• Fashion & Lifestyle — Produce editorial-quality imagery for campaigns.
• Creative Compositing — Combine elements from multiple reference images seamlessly.

Pro Tips

• Describe the style explicitly — include details like “film grain,” “warm retro tones,” or “editorial portrait.”
• Reference images guide the output — use clear, high-quality images for best results.
• Leave size empty to automatically preserve the original image proportions.
• Include setting and mood details (e.g., “classic diner neon sign at dusk”) for atmospheric results.
• Use 1–2 reference images for simpler edits; add a third for complex multi-element compositions.

Notes

• Both prompt and images are required fields.
• Maximum 3 reference images can be uploaded.
• If size is not specified, the model preserves the original image ratio.
• Resolution range: 256–1536 pixels for both width and height.

Related Models

• FireRed Image Edit — Previous version with multi-image composition.
• Qwen Image 2.0 Edit — Multi-image editing with Figure references.
• Seedream V5.0 Lite Edit — Style transfer and multi-reference editing.

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",
  "images": [
    "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/firered-image-v1.1/edit" \
  -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