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.
Idle
$0.038per run·~26 / $1
ExamplesView all
Miniature Chocolate Brand Fun
A young woman in her mid-20s sitting by a café window, wearing a beige sweater, holding a cup of coffee, natural morning sunlight on her face, candid street photography style.
A cheerful group of college friends taking a selfie in a park, casual outfits, green grass and blue sky behind them, authentic lifestyle photo.
A jogger running along a riverside path in the early morning, wearing sportswear, light fog over the water.
Epic fantasy art of a majestic white dragon with pearlescent scales, landing gracefully in a colossal underground cavern. The rider, a female elf in polished silver armor, dismounts. The cavern walls are lined with giant, glowing amethyst and quartz crystals that emit a soft, multi-colored ambient light. A serene underground lake reflects the shimmering crystals. The scene is peaceful and awe-inspiring, showcasing a hidden sanctuary. The crystals' light reflects beautifully off the dragon's scales and the elf's armor. Highly detailed, focusing on the interplay of light and reflective surfaces.
An ultra-photorealistic shot, capturing a lazy ginger cat sleeping peacefully on a stack of old books next to a window. Soft morning sunlight streams in, illuminating dust motes dancing in the air and highlighting the fine texture of the cat's fur and the worn paper of the books. A half-empty ceramic mug of tea sits nearby. The focus is sharp on the cat, with the rest of the cozy room gently blurred in the background. Shot with a Canon EOS R5, 50mm f/1.8 lens, natural lighting, serene and quiet mood.
A beautiful anime scene in the style of Studio Ghibli. A young girl in a simple summer dress sits alone on a weathered wooden bench at a rural bus stop in the Japanese countryside. It's late afternoon, and the sky is a soft orange. The bus stop is surrounded by lush, overgrown greenery and towering, vibrant green camphor trees. A single cicada is visible on the signpost. The atmosphere is peaceful, slightly nostalgic, and filled with the quiet hum of summer. Beautifully detailed hand-drawn background, soft, warm color palette.
An interior scene in a cozy, cluttered attic art studio, Hayao Miyazaki aesthetic. Sunlight filters through a large, round window, illuminating a wooden desk covered in art supplies: watercolor palettes, jars of brushes, scattered sketches, and a half-finished painting of a landscape. A warm cup of tea steams gently. The room is filled with books, hanging plants, and interesting trinkets. The feeling is one of creative solitude and peaceful messiness. Rich details, warm and inviting light.
A cinematic film still of a person walking alone down a dirt path in a dense, misty forest at dawn. Sunbeams (volumetric light) cut through the thick fog and canopy of tall pine trees, creating a magical, ethereal effect. The person is a small figure in the grand landscape, wearing a warm coat. The color grading is slightly desaturated with cool, muted tones, evoking a sense of quiet introspection and profound peace. Shot on Kodak Portra 400 film for a soft, grainy texture.
A gentle and soft digital watercolor illustration of a young woman seen from behind, holding a large, beautiful bouquet of wildflowers. She is standing in a vast field of tall grass at sunset. The colors are soft and blended, with translucent layers. The sky is a wash of pastel pink, orange, and lavender. The focus is on the delicate textures of the flowers and the soft, flowing lines of her hair and dress. The mood is serene, romantic, and deeply calming.
A vibrant, high-angle shot of a Solarpunk city sanctuary. Buildings are constructed with smooth, white bio-concrete and flowing organic shapes, seamlessly integrated with vertical gardens and cascading waterfalls. On a massive rooftop terrace, a diverse community of people tends to a lush hydroponic farm under a geodesic glass dome. Elegant, petal-shaped solar panels track the sun. Small transport drones hum quietly, carrying produce. The lighting is bright, clean, and optimistic, conveying a sense of community and harmony. Hyper-detailed, 8K
Related Models
README
Gemini 2.5 Flash Image — Google
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
- Enter your prompt describing the desired image or edit.
- Select the aspect ratio (e.g.,
16:9,3:2,1:1,9:16). - Choose the output format (
pngorjpeg). - (Optional) Enable sync mode for inline response generation.
- 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.
Gemini 2.5 Flash Image Text To Image API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/google/gemini-2.5-flash-image/text-to-image with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Gemini 2.5 Flash Image Text To Image below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/google/gemini-2.5-flash-image/text-to-image" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"output_format": "png",
"enable_sync_mode": false,
"enable_base64_output": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("google/gemini-2.5-flash-image/text-to-image", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"output_format": "png",
"enable_sync_mode": false,
"enable_base64_output": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"google/gemini-2.5-flash-image/text-to-image",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "1:1",
"output_format": "png",
"enable_sync_mode": false,
"enable_base64_output": false
}
)
print(output["outputs"][0]) # → URL of the generated outputGemini 2.5 Flash Image Text To Image API — Frequently asked questions
What is the Gemini 2.5 Flash Image Text To Image API?
Gemini 2.5 Flash Image Text To Image is a Google model for image generation, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.
How do I call the Gemini 2.5 Flash Image Text To Image API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/google/google-gemini-2.5-flash-image-text-to-image.
How much does Gemini 2.5 Flash Image Text To Image cost per run?
Gemini 2.5 Flash Image Text To Image starts at $0.038 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Gemini 2.5 Flash Image Text To Image accept?
Key inputs: `prompt`, `aspect_ratio`, `enable_base64_output`, `enable_sync_mode`, `output_format`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/google/google-gemini-2.5-flash-image-text-to-image.
How long does Gemini 2.5 Flash Image Text To Image take to generate?
Average end-to-end generation time on WaveSpeedAI is around 74 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Gemini 2.5 Flash Image Text To Image outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (Google). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.