Vectorizing Images

Recraft V4 and V4 Pro can generate vector graphics (SVG) directly from text prompts. Unlike raster image generation which produces pixel-based output, vectorization produces infinitely scalable SVG files — perfect for logos, icons, illustrations, and print materials.

Available models

Job Type	Resolution	ETA
inference.recraft.v4.txt2vec.v1	Up to 1536x768	~28s
inference.recraft.v4.pro.txt2vec.v1	Up to 3072x1536	~45s

V4 Pro generates at higher resolution with more detail, but takes longer.

Generate a vector image

prodia-js

main.js

import fs from "node:fs/promises";
import { createProdia } from "prodia/v2";

const prodia = createProdia({
  token: process.env.PRODIA_TOKEN,
});

const job = await prodia.job({
  type: "inference.recraft.v4.txt2vec.v1",
  config: {
    prompt: "a minimalist logo of a mountain range at sunset",
  },
});

const svg = await job.arrayBuffer();
await fs.writeFile("mountain.svg", new Uint8Array(svg));
console.log("Saved mountain.svg");

node main.js

requests

main.py

from requests.adapters import HTTPAdapter, Retry
import os
import requests
import sys

prodia_token = os.getenv('PRODIA_TOKEN')
prodia_url = 'https://inference.prodia.com/v2/job'

session = requests.Session()
retries = Retry(allowed_methods=None, status_forcelist=Retry.RETRY_AFTER_STATUS_CODES)
session.mount('http://', HTTPAdapter(max_retries=retries))
session.mount('https://', HTTPAdapter(max_retries=retries))
session.headers.update({'Authorization': f"Bearer {prodia_token}"})

job = {
    'type': 'inference.recraft.v4.txt2vec.v1',
    'config': {
        'prompt': 'a minimalist logo of a mountain range at sunset',
    },
}

res = session.post(prodia_url, json=job)
print(f"Request ID: {res.headers['x-request-id']}")
print(f"Status: {res.status_code}")

if res.status_code != 200:
    print(res.text)
    sys.exit(1)

with open('mountain.svg', 'wb') as f:
    f.write(res.content)

print("Saved mountain.svg")

python main.py

curl

main.sh

set -euo pipefail

job=$(cat <<EOF
{
  "type": "inference.recraft.v4.txt2vec.v1",
  "config": {
    "prompt": "a minimalist logo of a mountain range at sunset"
  }
}
EOF
)

curl -sSf \
  -H "Authorization: Bearer $PRODIA_TOKEN" \
  -H 'Accept: image/svg+xml' \
  --json "$job" \
  --output mountain.svg \
  --retry 3 \
  https://inference.prodia.com/v2/job

bash main.sh

macOS

open mountain.svg

Linux

xdg-open mountain.svg

Windows

start mountain.svg

Using V4 Pro for higher quality

Replace the job type with inference.recraft.v4.pro.txt2vec.v1 for higher resolution output:

main.js

const job = await prodia.job({
  type: "inference.recraft.v4.pro.txt2vec.v1",
  config: {
    prompt: "a minimalist logo of a mountain range at sunset",
    size: "2048x2048",
  },
});

Controlling colors

Both models support a controls parameter to specify color palettes and background colors:

main.js

const job = await prodia.job({
  type: "inference.recraft.v4.txt2vec.v1",
  config: {
    prompt: "a flat icon of a coffee cup",
    controls: {
      colors: [
        { rgb: [139, 90, 43] },
        { rgb: [255, 255, 255] },
      ],
      background_color: {
        rgb: [245, 245, 220],
      },
    },
  },
});

Output format

The response is an SVG file. SVGs are XML-based vector graphics that:

• Scale to any size without quality loss
• Are typically 100KB–1MB depending on complexity
• Can be opened in any browser, Figma, Illustrator, or Inkscape
• Can be embedded directly in HTML with <img src="output.svg">

Example outputs

Recraft V4 (inference.recraft.v4.txt2vec.v1):

Recraft V4 Pro (inference.recraft.v4.pro.txt2vec.v1):

Size options

V4 (default: 1024x1024):

1024x1024, 1536x768, 768x1536, 1280x832, 832x1280, 1216x896, 896x1216, 1152x896, 896x1152, 832x1344, 1280x896, 896x1280, 1344x768, 768x1344

V4 Pro (default: 2048x2048):

2048x2048, 3072x1536, 1536x3072, 2560x1664, 1664x2560, 2432x1792, 1792x2432, 2304x1792, 1792x2304, 1664x2688, 2560x1792, 1792x2560, 2688x1536, 1536x2688