Longcat Image Edit

Longcat Image Edit

Playground

LongCat-Image Edit is a 6B parameter bilingual (Chinese-English) image editing model from Meituan, excelling at multilingual text rendering, photorealism, and deployment efficiency. Ready-to-use REST inference API with best performance and no cold starts.

Features

LongCat-Image Edit is a 6B parameter image editing model from Meituan, designed for bilingual (Chinese-English) image editing with exceptional text rendering capabilities.

Where LongCat-Image Edit fits best

• Editing Chinese and English text in images
• Photorealistic image modifications
• Marketing and product visuals with text overlays
• Typography and layout updates in existing designs

Key Features

• Exceptional Efficiency and Performance

With only 6B parameters, LongCat-Image Edit delivers high-quality results while maintaining efficient resource usage.

• Powerful Chinese Text Rendering

Superior accuracy in rendering and editing Chinese characters with industry-leading Chinese dictionary coverage.

• Bilingual Support

Natively supports both Chinese and English prompts with excellent text rendering in both languages.

• Natural Language Editing

Describe edits in plain language to modify images while preserving the original composition.

Related Models on WaveSpeedAI

• LongCat-Image Text-to-Image – Text-to-image generation with the same bilingual capabilities.

More Image Tools on WaveSpeedAI

• Nano Banana Pro – Google’s Gemini-based text-to-image model for sharp, coherent, prompt-faithful visuals.
• Seedream V4 – style-consistent, multi-image generator ideal for posters and campaigns.
• Qwen Edit Plus – An enhanced Qwen-based image editor for precise inpainting and local style changes.

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",
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
  "output_format": "jpeg",
  "seed": -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/longcat-image/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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters