Next-Gen Image Generation & Editing: FLUX.1 Kontext Now Available on SiliconFlow

SiliconFlow today introduces FLUX.1 Kontext [pro] and FLUX.1 Kontext [max], a suite of generative flow matching models that allows you to generate and edit images at the next level. Unlike traditional text-to-image models, the FLUX.1 Kontext family supports in-context image generation with both text and image prompts, enabling users to seamlessly extract, reinterpret, and modify visual concepts to produce new and coherent outputs. Additionally, you can also access FLUX.1 Kontext [dev] on our platform, giving you the flexibility to choose the right model for your specific usecase.

With SiliconFlow's FLUX.1 Kontext API, you can expect:

• Accessible Pricing: FLUX.1-Kontext-pro: $0.04/ Image ; FLUX.1-Kontext-max: $0.08/ Image.

• Improved Text-to-Image Capabilities: Strong prompt following, photorealistic rendering, excellent typography.

• Flexible iterative image editing: Instant image editing with text commands, step-by-step iterative refinement with consistent quality.

Advanced Image Generation & Modification

SiliconFlow now features two new in-context image models from the FLUX.1 Kontext suite. From precise image generation to complex local edits, these models redefine what's possible in AI-powered image creation.

FLUX.1-Kontext-pro:

• Delivers local editing, generative in-context modifications and classic text-to-image generation.

• Accepts both text and image inputs, enabling flexible and targeted generation.

• Allows local edits in specific image regions and complex transformations of entire scenes.

• Enables multi-turn editing with consistent character, styles, and features across scenes and viewpoints.

FLUX.1-Kontext-max:

• Strong prompt adherence, typography generation and editing consistency.

• Maximum Performance mentioned above all without compromising speed.

FLUX.1 Kontext's Performance on SiliconFlow

FLUX.1 Kontext models surpass traditional text-to-image generation by understanding and creating from existing images. Now you can simply modify input images with text instructions for flexible, instant editing—no finetuning or complex workflows required.

Now let's explore how FLUX.1 Kontext's core capabilities perform.

*All images below are generated and edited by FLUX.1-Kontext-Pro on SiliconFlow.

Character Consistency

Preserve unique elements of an image, such as a reference character or object in a picture, across multiple scenes and environments.

Local Editing

Kontext can also make targeted modifications of specific elements in an image without affecting the rest. For example, you can change the text in the image below.

Style Reference

Generate novel scenes while preserving unique styles from a reference image, directed by text prompts.

Getting Started

Explore Kontext now via the SiliconFlow playground.

Or use our OpenAI-compatible API. Explore the full API specifications in the SiliconFlow API documentation.

import requests

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

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

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

print(response.text)

Whether you're crafting ad campaigns, building e-commerce content, or designing characters, FLUX.1 Kontext [pro] and [max] deliver fast, consistent image editing and generation to streamline your creative workflow.

Try them now on SiliconFlow for high-quality results at speed！