Examples for using imagen-4 through RunAPI from agent tools or API calls. Copy a prompt, then use it in Claude Code, Codex, Cursor, Windsurf, or your backend.
1. claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
2. Restart Claude Code
3. Paste this prompt: Generate an image: "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
1. codex plugin install runapi-mcp@agents
2. Restart Codex
3. Paste this prompt: Generate an image: "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
1. npx @runapi.ai/mcp init cursor
2. Restart Cursor
3. Paste this prompt: Generate an image: "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
1. npx @runapi.ai/mcp init windsurf
2. Restart Windsurf
3. Paste this prompt: Generate an image: "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "imagen-4",
"prompt": "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
}
JSON
import { Imagen4Client } from "@runapi.ai/imagen-4";
const client = new Imagen4Client({
apiKey: process.env.RUNAPI_API_KEY,
});
const result = await client.textToImage.run({
"model": "imagen-4",
"prompt": "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
});
console.log(result.id);
require "runapi/imagen_4"
client = RunApi::Imagen4::Client.new
result = client.text_to_image.run(
model: "imagen-4",
prompt: "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
)
puts result.id
package main
import (
"context"
"fmt"
"log"
"net/http"
"os"
"strings"
)
func main() {
body := strings.NewReader("{\"model\":\"imagen-4\",\"prompt\":\"A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera\"}")
req, err := http.NewRequestWithContext(context.Background(), http.MethodPost, "https://runapi.ai/api/v1/imagen_4/text_to_image", body)
if err != nil {
log.Fatal(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
req.Header.Set("Content-Type", "application/json")
resp, err := http.DefaultClient.Do(req)
if err != nil {
log.Fatal(err)
}
defer resp.Body.Close()
fmt.Println(resp.Status)
}
A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera
curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "imagen-4",
"prompt": "A fluffy white Persian cat with bright blue eyes sitting gracefully on a sunlit windowsill, soft morning light streaming through lace curtains creating gentle dappled shadows, warm golden tones, shallow depth of field with sharp focus on the cat's face, photorealistic, shot on medium format camera"
}
JSON
Vibrant product-on-moss hero shot for an eco sneaker brand. A single running shoe placed on a bed of fresh green moss, soft morning light filtering through trees above, minimal composition, forest green and cream color palette, natural outdoor product photography, 4:5 aspect ratio, no text.
curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "imagen-4",
"prompt": "Vibrant product-on-moss hero shot for an eco sneaker brand. A single running shoe placed on a bed of fresh green moss, soft morning light filtering through trees above, minimal composition, forest green and cream color palette, natural outdoor product photography, 4:5 aspect ratio, no text."
}
JSON
Editorial fashion photo of an African-American man in a black leather shearling jacket, leaning into a beige vintage car from the outside. The scene is viewed from inside the car looking out through the passenger window. Sharp shadows, clean directional light, and cinematic framing. A desert landscape stretches out behind him. Moody atmosphere. 35mm film look with subtle grain.
curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "imagen-4",
"prompt": "Editorial fashion photo of an African-American man in a black leather shearling jacket, leaning into a beige vintage car from the outside. The scene is viewed from inside the car looking out through the passenger window. Sharp shadows, clean directional light, and cinematic framing. A desert landscape stretches out behind him. Moody atmosphere. 35mm film look with subtle grain."
}
JSON
35mm film photograph of a floating island suspended above the Moscow skyline, dramatic cumulus clouds surrounding it, cinematic golden hour lighting, vintage aesthetic with warm color tones, subtle film grain texture, architectural fantasy concept
Historically informed oil-painting-style scene of an ancient Roman marketplace at midday. Wide angle showing a colonnade with merchants, shoppers in period-accurate togas and tunics, baskets of goods, terracotta pottery. Warm Mediterranean sunlight creating defined shadows under the columns. Clear focal areas drawing the eye from foreground commerce to background architecture. 3:2 aspect ratio, no text.
curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "imagen-4",
"prompt": "Historically informed oil-painting-style scene of an ancient Roman marketplace at midday. Wide angle showing a colonnade with merchants, shoppers in period-accurate togas and tunics, baskets of goods, terracotta pottery. Warm Mediterranean sunlight creating defined shadows under the columns. Clear focal areas drawing the eye from foreground commerce to background architecture. 3:2 aspect ratio, no text."
}
JSON
Environmental portrait of an elderly Japanese woodworker in his cluttered workshop. He holds a hand plane (kanna) at chest height, examining its blade with quiet concentration. Late afternoon sunlight enters through a small dusty window, catching wood shavings suspended in the air. His hands are weathered and precise. Shallow depth of field isolates him from shelves of chisels and saws behind him. Natural color palette dominated by warm wood tones. Documentary photography style, no posing, candid moment.
curl -X POST https://runapi.ai/api/v1/imagen_4/text_to_image \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'JSON'
{
"model": "imagen-4",
"prompt": "Environmental portrait of an elderly Japanese woodworker in his cluttered workshop. He holds a hand plane (kanna) at chest height, examining its blade with quiet concentration. Late afternoon sunlight enters through a small dusty window, catching wood shavings suspended in the air. His hands are weathered and precise. Shallow depth of field isolates him from shelves of chisels and saws behind him. Natural color palette dominated by warm wood tones. Documentary photography style, no posing, candid moment."
}
JSON
FAQ
Using imagen-4 prompts
What is %{model}?
%{model} is available through RunAPI as part of the unified model catalog. These prompts show practical input patterns that agents and backend services can reuse.
How do I use these prompts?
Copy any prompt and paste it into Claude Code, Codex, Cursor, or Windsurf after installing the RunAPI MCP Server. Developers can also copy the API example and send the prompt directly.
Do these prompts cost money to browse?
Browsing and copying prompt examples is free. Generation requests only cost money when you call a RunAPI model with your API key.
Can I adapt the prompts for production?
Yes. Treat each prompt as a starting point, then add your brand rules, output dimensions, safety constraints, and application-specific context before using it in production.