Generate & Edit

Generate and edit images from text prompts, sketches, or existing images with creative control. Perfect for creative content generation, marketing and advertising, product visualization, and artistic expression.

Image generation example showing AI-generated images from text prompts with creative control

Text-to-Image — Examples of image generation supported.

Image-Inpainting — Examples of image generation supported.

Example Usage

For best results, we recommend using the Structured Outputs API to get responses in a structured and validated data format.

Text-to-Image

Generate images from text descriptions with creative control over style, composition, and details. Generate an image of a cat flying through the sky and clouds, with the background of a green city with river

from vlmrun.client import VLMRun

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Generate the image
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": "Generate an image of a modern building as a cyberpunk-style futuristic structure with neon lights and holographic elements"
        }
    ]
)

print(response.choices[0].message.content)
# >>> {"url": "https://.../image.jpg"}

from vlmrun.client import VLMRun
from pydantic import BaseModel, Field

# Define the response schema
class ImageGenerationResponse(BaseModel):
  url: str = Field(..., description="The URL of the generated image")

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Generate the image with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": "Generate an image of a modern building as a cyberpunk-style futuristic structure with neon lights and holographic elements"
        }
    ],
    response_format={"type": "json_schema", "schema": ImageGenerationResponse.model_json_schema()}
)

# Validate the response
result = ImageGenerationResponse.model_validate_json(response.choices[0].message.content)
# >>> ImageGenerationResponse(url="https://.../image.jpg")

import { VlmRun } from "vlmrun";

const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: "Generate an image of a modern building as a cyberpunk-style futuristic structure with neon lights and holographic elements"
    }
  ]
});

console.log(response.choices[0].message.content);

import { VlmRun } from "vlmrun";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";

// Define the response schema with Zod
const ImageGenerationResponseSchema = z.object({
  url: z.string().describe("The URL of the generated image")
});

// Initialize the VLMRun client
const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

// Generate the image with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: "Generate an image of a modern building as a cyberpunk-style futuristic structure with neon lights and holographic elements"
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(ImageGenerationResponseSchema)
  }
});

const result = ImageGenerationResponseSchema.parse(JSON.parse(response.choices[0].message.content));

Image-to-Image

Transform existing images by applying new styles, enhancing details, or changing specific elements while preserving the original structure.

Reference Dog Image — Examples of image inputs for inpainting.

More examples of image-to-image — Examples of image inputs for inpainting.

from vlmrun.client import VLMRun

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Generate the image
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Transform the image of my dog on the right into a flying dog with superman cape, with majestic background"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dog-cat.jpg", "detail": "auto"}}
            ]
        }
    ]
)

print(response.choices[0].message.content)
# >>> {"url": "https://.../image.jpg"}

from vlmrun.client import VLMRun
from pydantic import BaseModel, Field

# Define the response schema
class ImageGenerationResponse(BaseModel):
  url: str = Field(..., description="The URL of the generated image")

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Transform the image with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Transform the image of my dog on the right into a flying dog with superman cape, with majestic background"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dog-cat.jpg", "detail": "auto"}}
            ]
        }
    ],
    response_format={"type": "json_schema", "schema": ImageGenerationResponse.model_json_schema()}
)

# Validate the response
result = ImageGenerationResponse.model_validate_json(response.choices[0].message.content)

import { VlmRun } from "vlmrun";

const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Transform the image of my dog on the right into a flying dog with superman cape, with majestic background" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dog-cat.jpg", detail: "auto" } }
      ]
    }
  ]
});

console.log(response.choices[0].message.content);

import { VlmRun } from "vlmrun";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";

// Define the response schema with Zod
const ImageGenerationResponseSchema = z.object({
  url: z.string().describe("The URL of the generated image")
});

// Initialize the VLMRun client
const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

// Transform the image with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Transform the image of my dog on the right into a flying dog with superman cape, with majestic background" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dog-cat.jpg", detail: "auto" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(ImageGenerationResponseSchema)
  }
});

const result = ImageGenerationResponseSchema.parse(JSON.parse(response.choices[0].message.content));

Image Inpainting

Fill in missing areas, remove unwanted objects, or add new elements to existing images seamlessly.

Reference Car Image — Examples of image inputs for inpainting.

from vlmrun.client import VLMRun

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Generate the image
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Given two images: the first with a dog in front holding a yellow ball, inpaint her driving the car shown in the second image."},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dogs.jpg", "detail": "auto"}},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.caption/car.jpg", "detail": "auto"}}
            ]
        }
    ]
)

print(response.choices[0].message.content)
# >>> {"url": "https://.../image.jpg"}

from vlmrun.client import VLMRun
from pydantic import BaseModel, Field

# Define the response schema
class ImageGenerationResponse(BaseModel):
  url: str = Field(..., description="The URL of the generated image")

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Inpaint the image with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Given two images: the first with a dog in front holding a yellow ball, inpaint her driving the car shown in the second image."},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dogs.jpg", "detail": "auto"}},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.caption/car.jpg", "detail": "auto"}}
            ]
        }
    ],
    response_format={"type": "json_schema", "schema": ImageGenerationResponse.model_json_schema()}
)

# Validate the response
result = ImageGenerationResponse.model_validate_json(response.choices[0].message.content)

import { VlmRun } from "vlmrun";

const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Given two images: the first with a dog in front holding a yellow ball, inpaint her driving the car shown in the second image." },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dogs.jpg", detail: "auto" } },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.caption/car.jpg", detail: "auto" } }
      ]
    }
  ]
});

console.log(response.choices[0].message.content);

import { VlmRun } from "vlmrun";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";

// Define the response schema with Zod
const ImageGenerationResponseSchema = z.object({
  url: z.string().describe("The URL of the generated image")
});

// Initialize the VLMRun client
const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

// Inpaint the image with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Given two images: the first with a dog in front holding a yellow ball, inpaint her driving the car shown in the second image." },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/dogs.jpg", detail: "auto" } },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.caption/car.jpg", detail: "auto" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(ImageGenerationResponseSchema)
  }
});

const result = ImageGenerationResponseSchema.parse(JSON.parse(response.choices[0].message.content));

Style Transfer

Apply artistic styles from reference images to transform the visual appearance while preserving content. In the example below, we apply the Van Gogh’s “Starry Night” painting style to a photo of a city skyline at night.

Reference Van Gogh Image — Examples of image inputs for style transfer.

Reference City Image — Examples of image inputs for style transfer.

from vlmrun.client import VLMRun

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Generate the image
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Given two images: the first with a Van Gogh painting, and the second with a city skyline at night, apply the Van Gogh painting style to the city skyline."},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/starry-night.jpg", "detail": "auto"}},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/sf-golden-gate.jpg", "detail": "auto"}}
            ]
        }
    ]
)

print(response.choices[0].message.content)
# >>> {"url": "https://.../image.jpg"}

from vlmrun.client import VLMRun
from pydantic import BaseModel, Field

# Define the response schema
class ImageGenerationResponse(BaseModel):
  url: str = Field(..., description="The URL of the generated image")

# Initialize the VLMRun client
client = VLMRun(api_key="<VLMRUN_API_KEY>")

# Apply style transfer with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Given two images: the first with a Van Gogh painting, and the second with a city skyline at night, apply the Van Gogh painting style to the city skyline."},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/starry-night.jpg", "detail": "auto"}},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/sf-golden-gate.jpg", "detail": "auto"}}
            ]
        }
    ],
    response_format={"type": "json_schema", "schema": ImageGenerationResponse.model_json_schema()}
)

# Validate the response
result = ImageGenerationResponse.model_validate_json(response.choices[0].message.content)

import { VlmRun } from "vlmrun";

const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Given two images: the first with a Van Gogh painting, and the second with a city skyline at night, apply the Van Gogh painting style to the city skyline." },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/starry-night.jpg", detail: "auto" } },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/sf-golden-gate.jpg", detail: "auto" } }
      ]
    }
  ]
});

console.log(response.choices[0].message.content);

import { VlmRun } from "vlmrun";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";

// Define the response schema with Zod
const ImageGenerationResponseSchema = z.object({
  url: z.string().describe("The URL of the generated image")
});

// Initialize the VLMRun client
const client = new VlmRun({
  apiKey: "<VLMRUN_API_KEY>",
  baseURL: "https://api.vlm.run/v1"
});

// Apply style transfer with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Given two images: the first with a Van Gogh painting, and the second with a city skyline at night, apply the Van Gogh painting style to the city skyline." },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/starry-night.jpg", detail: "auto" } },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.generation/sf-golden-gate.jpg", detail: "auto" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(ImageGenerationResponseSchema)
  }
});

const result = ImageGenerationResponseSchema.parse(JSON.parse(response.choices[0].message.content));

FAQ

Suggest the supported styles for image generation?

Photorealistic: Ultra-realistic images with fine details
High Detail: Ultra-realistic images with fine details
Natural Lighting: Realistic lighting and shadows
Professional Quality: Suitable for commercial and professional use
Multiple Subjects: People, objects, landscapes, architecture

What are some tips for creating effective prompts?

Be Specific: Include details about style, composition, lighting, and mood
Use Keywords: Include relevant art terms, techniques, and descriptors
Reference Styles: Mention specific artists, art movements, or visual styles
Technical Details: Specify resolution, quality, and output format needs

Get Started

Concepts

Image Capabilities

Document Capabilities

Video Capabilities

Pricing

Misc

Generate & Edit

Example Usage

Text-to-Image

Image-to-Image

Image Inpainting

Style Transfer

FAQ

​Example Usage

​Text-to-Image

​Image-to-Image

​Image Inpainting

​Style Transfer

​FAQ

Example Usage

Text-to-Image

Image-to-Image

Image Inpainting

Style Transfer

FAQ