Google Gemini 2.5 Flash Image Preview Edit
Playground
Try it on WaveSpeedAI!Google Gemini 2.5 Flash Image Preview is an image-to-image editing model with advanced creative controls for precise image edits. 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. It is a new variant of the Gemini 2.5 family, specifically designed for fast, conversational, and multi-turn creative workflows. This model is made available to developers through the Gemini API, Google AI Studio, and Vertex AI.
Key Features
- Native Image Generation and Editing: Gemini 2.5 Flash Image is a multimodal model that natively understands and generates images. This allows for a seamless, unified workflow for creating and editing visuals.
- Multi-image Fusion: This powerful feature allows you to combine multiple input images into a single, cohesive, new visual. For example, you can integrate a product into a new scene or restyle a room by merging images of different furniture and decor.
- Character and Style Consistency: A significant advancement is the ability to maintain a consistent character, object, or style across multiple prompts and images. This is essential for storytelling, branding, and generating a series of cohesive assets without needing time-consuming fine-tuning.
- Conversational Editing: The model enables precise, targeted edits using natural language. You can make specific changes like blurring a background, removing an object, altering a subject’s pose, or colorizing a black-and-white photo by simply describing the desired outcome.
- Visual Reasoning: Gemini 2.5 Flash Image benefits from the Gemini model’s deep world knowledge. It can go beyond simple photorealism to perform complex tasks that require genuine understanding, such as interpreting hand-drawn diagrams, assisting with educational queries, and following multi-step instructions.
- SynthID Watermarking: To promote responsible AI and transparency, all images created or edited with Gemini 2.5 Flash Image are embedded with an invisible digital watermark from SynthID. This watermark helps identify the content as AI-generated or edited.
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=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"aspect_ratio": "1:1",
"output_format": "png"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/google/gemini-2.5-flash-image-preview/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
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| images | array<string> | Yes | - | 1 ~ 10 items | List of URLs of input images for editing. Up to 10 images can be provided. |
| aspect_ratio | string | No | - | 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 | The aspect ratio of the generated media. |
| output_format | string | No | png | png, jpeg | The format of the output image. |
| enable_sync_mode | boolean | No | false | - | If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models. |
| enable_base64_output | boolean | No | false | - | If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |