Image Tools

Use the Structured Outputs API for structured, validated responses.

1. Image Cropping

One request can crop several regions.

Crop the clock to tell the time more clearly.

from vlmrun.client import VLMRun

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

# Crop image to focus on main subject
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Crop the clock to tell the time more clearly"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/clock.jpg", "detail": "auto"}}
            ]
        }
    ]
)

print(response.choices[0].message.content)
# >>> {"url": "https://.../cropped.jpg", "label": "clock", "xywh": [0.2, 0.2, 0.6, 0.6]}

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

# Define the response schema
class ImageCropResponse(BaseModel):
    url: str = Field(..., description="URL of the cropped image")
    label: str = Field(..., description="Object label")
    xywh: tuple[float, float, float, float] = Field(..., description="Bounding box (x, y, w, h)")

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

# Crop image with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Crop the clock to tell the time more clearly"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/clock.jpg", "detail": "auto"}}
            ]
        }
    ],
    response_format={"type": "json_schema", "schema": ImageCropResponse.model_json_schema()}
)

# Validate the response
result = ImageCropResponse.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: "Crop the clock to tell the time more clearly" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/clock.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 ImageCropResponseSchema = z.object({
  url: z.string().describe("URL of the cropped image"),
  label: z.string().describe("Object label"),
  xywh: z.array(z.number()).describe("Bounding box (x, y, w, h)")
});

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

// Crop image with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Crop the clock to tell the time more clearly" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/clock.jpg", detail: "auto" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(ImageCropResponseSchema)
  }
});

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

2. Image Rotation

Allowed angles are 0, 90, 180, and 270 degrees clockwise.

Rotate the image 90 degrees clockwise to correct the orientation.

Original image before rotation — Rotated 90 degrees clockwise.

Image after 90-degree rotation in the clockwise direction — Rotated 90 degrees clockwise.

from vlmrun.client import VLMRun

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

# Rotate image to correct orientation
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Rotate this image 90 degrees clockwise"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/cats.jpg"}}
            ]
        }
    ]
)

print(response.choices[0].message.content)
# >>> {"url": "https://.../rotated.jpg", "angle": 90}

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

# Define the response schema
class ImageRotationResponse(BaseModel):
    url: str = Field(..., description="URL of the rotated image")
    angle: int = Field(..., description="Rotation angle (0, 90, 180, 270) degrees clockwise")

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

# Rotate image with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Rotate this image 90 degrees clockwise"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/cats.jpg"}}
            ]
        }
    ],
    response_format={"type": "json_schema", "schema": ImageRotationResponse.model_json_schema()}
)

# Validate the response
result = ImageRotationResponse.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: "Rotate this image 90 degrees clockwise" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/cats.jpg" } }
      ]
    }
  ]
});

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 ImageRotationResponseSchema = z.object({
  url: z.string().describe("URL of the rotated image"),
  angle: z.number().int().describe("Rotation angle (0, 90, 180, 270) degrees clockwise")
});

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

// Rotate image with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Rotate this image 90 degrees clockwise" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.object-detection/cats.jpg" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(ImageRotationResponseSchema)
  }
});

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

3. Super-Resolution Enhancement

Scales are 2x, 4x, and 8x.

Enhance this image using super-resolution to increase its resolution while preserving quality.

Original low-resolution image — 4x upscale.

Enhanced high-resolution image — 4x upscale.

from vlmrun.client import VLMRun

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

# Apply super-resolution enhancement
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Enhance this image using super-resolution to increase its resolution while preserving quality"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/vegetables-lo.jpg"}}
            ]
        }
    ]
)

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

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

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

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

# Enhance image with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Enhance this image using super-resolution to increase its resolution while preserving quality"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/vegetables-lo.jpg"}}
            ]
        }
    ],
    response_format={"type": "json_schema", "schema": SuperResolutionResponse.model_json_schema()}
)

# Validate the response
result = SuperResolutionResponse.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: "Enhance this image using super-resolution to increase its resolution while preserving quality" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/vegetables-lo.jpg" } }
      ]
    }
  ]
});

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 SuperResolutionResponseSchema = z.object({
  url: z.string().describe("URL of the enhanced image")
});

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

// Enhance image with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "Enhance this image using super-resolution to increase its resolution while preserving quality" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/vegetables-lo.jpg" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(SuperResolutionResponseSchema)
  }
});

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

4. De-Oldify (Colorization)

Colorize a black-and-white or sepia image.

De-oldify this image so that it's colorized and upsampled.

Original black and white image — Colorized black-and-white photo.

Colorized image with realistic colors — Colorized black-and-white photo.

from vlmrun.client import VLMRun

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

# Colorize black and white image
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "De-oldify this image so that it's colorized and upsampled"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/lunch-skyscraper.jpg"}}
            ]
        }
    ]
)

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

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

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

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

# Colorize image with structured output
response = client.agent.completions.create(
    model="vlmrun-orion-1:auto",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "De-oldify this image so that it's colorized and upsampled"},
                {"type": "image_url", "image_url": {"url": "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/lunch-skyscraper.jpg"}}
            ]
        }
    ],
    response_format={"type": "json_schema", "schema": DeOldifyResponse.model_json_schema()}
)

# Validate the response
result = DeOldifyResponse.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: "De-oldify this image so that it's colorized and upsampled" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/lunch-skyscraper.jpg" } }
      ]
    }
  ]
});

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 DeOldifyResponseSchema = z.object({
  url: z.string().describe("URL of the colorized image")
});

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

// Colorize image with structured output
const response = await client.agent.completions.create({
  model: "vlmrun-orion-1:auto",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "De-oldify this image so that it's colorized and upsampled" },
        { type: "image_url", image_url: { url: "https://storage.googleapis.com/vlm-data-public-prod/hub/examples/image.agent/lunch-skyscraper.jpg" } }
      ]
    }
  ],
  response_format: {
    type: "json_schema",
    schema: zodToJsonSchema(DeOldifyResponseSchema)
  }
});

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

FAQ

What image formats are supported for editing?

JPEG/JPG
PNG
TIFF
WebP
BMP

Overview

Orion

Input & Outputs

Skills

Platform

Observability

Frameworks

Integrations

1. Image Cropping

2. Image Rotation

3. Super-Resolution Enhancement

4. De-Oldify (Colorization)

FAQ

​1. Image Cropping

​2. Image Rotation

​3. Super-Resolution Enhancement

​4. De-Oldify (Colorization)

​FAQ

1. Image Cropping

2. Image Rotation

3. Super-Resolution Enhancement

4. De-Oldify (Colorization)

FAQ