FLUX.1 Kontext Dev on SiliconFlow：Redefining Ultra-Fast, Context-Aware Image Editing

FLUX.1 Kontext Dev, the world’s fastest and best context-aware open image editing model by Black Forest Labs, is now officially available on SiliconFlow.

• High-Resolution Output: Supports consistent high-quality image rendering with pixel-level layout control.

• Cost-effective Pricing: 0.015$ / Image.

Key capabilities

Powered by SiliconFlow’s high-performance inference engine, FLUX.1 Kontext Dev delivers significantly faster inference and lower memory consumption, while preserving high-quality, precise image editing performance.

• Iterative Editing: Enables iterative editing with maintained consistency across multiple rounds.

• Character Preservation: Excels at character preservation across a diverse set of scenes and environments.

• Precise Editing Control: Allows both precise local and global edits.

Quick Start

Try the FLUX.1 Kontext Dev on the SiliconFlow playground.

Quick Access to API

The following Python example demonstrates how to invoke SiliconFlow’s API to perform context-aware image editing using the FLUX.1 Kontext Dev model.

import requests

url = "https://api.ap.siliconflow.com/v1/images/generations"

payload = {
    "model": "black-forest-labs/FLUX.1-Kontext-dev",
    "prompt": "an island near sea, with seagulls, moon shining over the sea, light house, boats int he background, fish flying over the sea",
    "image": "data:image/png;base64, XXX",
    "seed": 4999999999,
    "prompt_enhancement": False
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.request("POST", url, json=payload, headers=headers)

print(response.text)

Whether you’re an illustrator, concept artist, filmmaker, or product designer, FLUX.1 Kontext Dev empowers creators and developers to achieve ultra-fast, context-aware image editing with unparalleled precision and consistency.

Now it’s time to elevate your artistry and accelerate your workflow. Try FLUX.1 Kontext Dev today on SiliconFlow.