Google Gemini 2.5 Flash Image Text To Image API Documentation

Google Gemini 2.5 Flash Image Text To Image API Documentation

Playground

Google Gemini 2.5 Flash Image offers advanced text-to-image generation and image editing with creative controls for quality images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Gemini 2.5 Flash Image is Google’s state-of-the-art image generation and editing model, part of the Gemini 2.5 family. It’s optimized for fast, conversational, and multi-turn creative workflows, enabling high-quality visual generation and editing within seconds.

✨ Key Features

• Native Image Generation & Editing Natively supports both creation and modification of images, offering a seamless multimodal workflow.

• Multi-Image Fusion Combine multiple inputs into one cohesive image — perfect for product mockups, scene compositing, and style fusion.

• Character & Style Consistency Maintains consistent appearance, identity, and aesthetic across prompts and sessions, ideal for storytelling and branding.

• Conversational Editing Make precise visual changes simply by describing them in natural language (e.g., “remove the shadow,” “add a sunset glow”).

• Visual Reasoning Performs complex understanding tasks such as diagram interpretation, layout composition, and conceptual illustration.

• SynthID Watermarking All generated and edited images include Google’s invisible SynthID watermark for responsible AI use and transparency.

🧩 How to Use

1. Enter your prompt describing the desired image or edit.
2. Select the aspect ratio (e.g., 16:9, 3:2, 1:1, 9:16).
3. Choose the output format (png or jpeg).
4. (Optional) Enable sync mode for inline response generation.
5. Click Run to create your image instantly.

💰 Pricing

• $0.038 per image generation

📝 Notes

• Works best with descriptive, context-rich prompts that include composition and style details.
• Supports aspect ratios up to 21:9 for wide cinematic frames.
• Output format supports PNG (for transparent graphics) and JPEG (for compressed photography).
• Please follow Google’s model usage policies.
• If your input violates the safety rules, the system will block generation and return an error message.

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",
  "aspect_ratio": "1:1",
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/gemini-2.5-flash-image/text-to-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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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