Hunyuan Image 3 Instruct Edit

Hunyuan Image 3 Instruct Edit

Playground

Hunyuan Image 3.0 Instruct Edit – instruction-based image editing with natural language prompts, supporting up to 2 reference images for precise modifications. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Hunyuan Image 3 Instruct Edit is Tencent’s advanced image editing model that transforms existing images based on text instructions. Upload your source images and describe the changes you want — the model intelligently edits while preserving the original style and composition.

Why Choose This?

• Text-driven editing Modify images using natural language instructions for intuitive control.

• Multi-image input Support for multiple reference images to guide complex edits.

• Context-aware modifications Understands scene structure and object relationships for coherent edits.

• Multiple aspect ratios Preset options for 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.

• Flexible sizing Custom width and height from 256 to 1536 pixels.

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

Parameters

How to Use

1. Upload your images — add one or more source images by clicking ”+ Add Item”.
2. Write your prompt — describe the edits you want (add, remove, modify elements).
3. Select size preset — choose an aspect ratio that fits your needs.
4. Adjust dimensions (optional) — fine-tune width and height if needed.
5. Set seed (optional) — use a fixed seed for reproducible results.
6. Run — submit and download your edited image.

Pricing

Best Use Cases

• Photo Retouching — Remove unwanted objects, fix imperfections, enhance details.
• Creative Editing — Transform scenes, change backgrounds, add artistic elements.
• Product Photography — Modify product images, change colors, adjust compositions.
• Content Creation — Adapt existing visuals for different contexts and platforms.
• Design Iteration — Quickly explore variations of existing artwork.

Pro Tips

• Use clear, specific instructions for best results (e.g., “remove the person in the background” instead of “clean up the image”).
• Upload high-quality source images for better editing results.
• Use the Prompt Enhancer to refine your editing instructions.
• Multiple images can provide additional context for complex edits.
• Keep the same seed when comparing different edit instructions.

Notes

• Both prompt and images are required fields.
• Ensure uploaded image URLs are publicly accessible.
• Resolution range is 256-1536 pixels for both width and height.
• For best quality, match output dimensions to your source image aspect ratio.

Related Models

• Hunyuan Image 3 Instruct — Text-to-image generation with the same model family.
• Qwen-Image Edit-Plus — Advanced image editing with bilingual text support.

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"
  ],
  "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/hunyuan-image-3-instruct/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