Skip to main content
Image upscaling improves the resolution and visual quality of an existing image. Send a base64-encoded image to /image/upscale, choose a scale factor, and Venice returns the enhanced image as binary data. Use image upscaling when you already have an image and want a higher-resolution output. Use image generation when you need to create an image from a prompt, and image editing when you need to change image content.

​
Basic Usage

import base64
import os
from pathlib import Path

import requests

image_base64 = base64.b64encode(Path("input.jpg").read_bytes()).decode("utf-8")

response = requests.post(
    "https://api.venice.ai/api/v1/image/upscale",
    headers={
        "Authorization": f"Bearer {os.environ['VENICE_API_KEY']}",
        "Content-Type": "application/json",
    },
    json={
        "image": image_base64,
        "scale": 2,
    },
)

response.raise_for_status()
Path("upscaled.png").write_bytes(response.content)

import { readFile, writeFile } from "node:fs/promises";

const image = await readFile("input.jpg");

const response = await fetch("https://api.venice.ai/api/v1/image/upscale", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VENICE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    image: image.toString("base64"),
    scale: 2,
  }),
});

if (!response.ok) {
  throw new Error(await response.text());
}

const output = Buffer.from(await response.arrayBuffer());
await writeFile("upscaled.png", output);

IMAGE_BASE64=$(base64 < input.jpg | tr -d '\n')

curl https://api.venice.ai/api/v1/image/upscale \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"image\": \"$IMAGE_BASE64\",
    \"scale\": 2
  }" \
  --output upscaled.png

​
Parameters

ParameterTypeRequiredDescription
imagestringYesBase64-encoded source image.
scalenumberNoUpscale factor. Use the supported values listed by the API reference and model catalog.
The response is binary image data, not JSON. Write the response body directly to a file or stream it to storage.

​
Input Tips

  • Start with the cleanest source image you have. Upscaling improves detail, but it cannot fully recover information that is not present.
  • Use moderate scale factors for production workflows. Very large outputs can increase latency and file size.
  • Keep the original image around if you need to compare quality or retry with different settings.