Runware logoRunware

FLUX.2 [max]

The latest state-of-the-art model from Black Forest Labs, generating images grounded in live web information.

4519c9f8-ce15-40ec-8a48-0f4ad16159af

FLUX.2 [max] is a high-precision text to image and image editing model from Black Forest Labs that generates visuals grounded in real-time information via live web search. It delivers maximum prompt adherence with multi-reference editing and state-of-the-art consistency across identities, objects, and details.

Black Forest Labs
Commercial use
Text to ImageImage to Image
Output images cost $0.07 for the first megapixel, then $0.03 per additional megapixel. Reference images cost an additional $0.03 per megapixel.
1024x1024$0.07
1536x1024$0.10
1024x1536$0.10
1920x1080$0.13
1024x1024 · 1 reference (1920x1080)$0.16
1024x1024 · 3 references (1024x1024)$0.16

Examples

4c9b0974-87ec-4444-8d23-262d97d9e75a
85de3886-04b0-4c41-9737-ab259f32cbe7
f1a0e003-11e1-4c84-8800-37a0342acfb6
94a03d40-2031-41cb-9896-94d5ee87fe02
b652f446-c58e-49e3-9604-3a83c4b6e98e
b6402b0c-f2d6-4043-82bc-c3ec74f597a0
9d168994-1dc1-4536-a48c-d4631390b832
d27116ee-8c7e-4e6a-8cf3-bbaeb870f722
b2a1045a-99cf-470c-a306-58125ed660d0

README

Overview

FLUX.2 [max] is a high-quality image generation and editing model from Black Forest Labs, designed for creative and commercial workflows that require strong prompt adherence, visual consistency, and reliable real-world context. It sits at the premium end of the FLUX.2 model family and is well suited to use cases where accuracy, grounding, and controlled output matter.

In addition to generating polished visual content, FLUX.2 [max] can produce images grounded in up-to-date, real-world information when paired with external context. This makes it useful for scenarios such as visualising current products, events, locations, or trends, where prompts benefit from factual or time-sensitive inputs rather than purely synthetic imagination.

How it Works

FLUX.2 [max] is part of the FLUX.2 architecture family, combining a latent flow-matching backbone with a vision-language system capable of incorporating both prompt instructions and external context.

Prompt Interpretation

The model processes natural language prompts to understand composition, style, subject relationships, lighting, and intent. It performs well with longer, structured prompts and can incorporate injected context such as real-world data or search results when provided by the application layer.

Image Generation

FLUX.2 [max] generates high-resolution images with an emphasis on clean composition, stable structure, and visual coherence. It is designed to handle complex constraints without drifting from the original intent of the prompt.

Grounded & Context-Aware Generation

When supplied with external context, such as web search results or structured real-world information, FLUX.2 [max] can ground its outputs in factual data. This allows images to reflect current products, known entities, or recent events, rather than relying solely on generic or outdated priors.

Multi-Reference Editing

The model supports multiple reference images, enabling it to combine identity, layout, colour, and stylistic cues into a single output. This is particularly useful for workflows that require consistency across iterations or variations.

Key Features

  • High-Quality Image Output
    Produces detailed, well-composed images suitable for professional creative workflows.

  • Strong Prompt Adherence
    Accurately follows complex instructions around composition, materials, lighting, and style.

  • Grounded Image Generation
    Supports context-aware outputs when paired with real-world or search-derived information.

  • Multi-Reference Support
    Combines multiple reference images to preserve visual consistency across outputs.

  • Production-Focused Design
    Well suited to marketing imagery, product visuals, editorial assets, and concept frames.

Technical Specifications

  • Model Name: FLUX.2 [max]
  • Model Type: Image generation and multi-reference image editing
  • Input: Text prompt with optional reference images and external context
  • Prompt Handling: Optimised for detailed, structured prompts
  • Architecture: FLUX.2 latent flow-matching architecture with integrated vision-language understanding
  • Model Family: FLUX.2 [max], FLUX.2 [pro], FLUX.2 [flex], FLUX.2 [dev]

How to Use

  1. Write a prompt describing the subject, composition, lighting, and visual style.
  2. Optionally include reference images to guide consistency.
  3. If required, inject real-world context or structured data to ground the generation.
  4. Submit the request using the FLUX.2 [max] model.
  5. Review and iterate as needed.

Example prompt:
Create a clean, slightly angled isometric 3D illustration of San Francisco, highlighting recognisable landmarks such as the Golden Gate Bridge and the surrounding hills. Use soft, stylised geometry with realistic materials, subtle surface detail, and natural daylight with gentle shadows. Reflect the current weather conditions in the scene, including sky colour, lighting, and atmosphere. Keep the composition minimal with a calm, solid background. At the top of the image, place the city name “San Francisco” in bold text, with a weather icon below it, followed by today’s date in small text and the current temperature in medium-sized text. Ensure all text is centred, evenly spaced, and integrated cleanly with the scene without overwhelming the buildings.

Tips for Better Results

  • Use grounded context when accuracy or recency matters.
  • Keep prompts structured and explicit, especially when combining creative and factual requirements.
  • Use reference images to stabilise composition and identity.
  • Avoid overloading the prompt; introduce constraints gradually.

Notes & Limitations

  • Grounded generation depends on the quality and clarity of the external context provided.
  • FLUX.2 [max] prioritises consistency and control over rapid experimentation.
  • For lower-cost iteration or exploratory work, other FLUX.2 variants may be more appropriate.

Documentation

You can find full usage details, parameters, and examples here: https://runware.ai/docs/en/providers/bfl

More models from this creator

View Model
FLUX.2 [klein] 9B

FLUX.2 [klein] 9B

FLUX.2 [klein] 9B is a 4-step distilled image generation and editing model designed for sub-second inference without sacrificing visual quality. It unifies text-to-image and advanced editing workflows in a single model, making it suitable for interactive applications, real-time previews, and latency-critical production use.

View Model
FLUX.2 [klein] 4B

FLUX.2 [klein] 4B

FLUX.2 [klein] 4B is a 4-step distilled image generation and editing model optimized for ultra-low latency inference. It delivers near real-time performance with strong visual quality, enabling interactive workflows and responsive production systems on more constrained hardware.

View Model
FLUX.2 [klein] 9B Base

FLUX.2 [klein] 9B Base

FLUX.2 [klein] 9B Base is the undistilled foundation model of the Klein family, offering full model capacity for image generation and editing. It is optimized for fine-tuning, customization, and post-training workflows where flexibility, control, and maximum training signal are required.

View Model
FLUX.2 [klein] 4B Base

FLUX.2 [klein] 4B Base

FLUX.2 [klein] 4B Base is a compact undistilled image generation and editing model with an exceptional quality-to-size ratio. It is well suited for local deployment, efficient fine-tuning, and custom pipelines that require flexibility on limited hardware.

View Model
FLUX.2 [pro]

FLUX.2 [pro]

FLUX.2 [pro] is a flow-matching latent transformer for precise text-to-image synthesis and reference-guided editing. It supports multi image references, 4MP outputs, and Mistral-based text conditioning for controllable composition and robust iterative edits that preserve structure.

View Model
FLUX.2 [dev]

FLUX.2 [dev]

FLUX.2 dev is an open weight text to image and image editing model from Black Forest Labs. It targets developers who need precise control over prompts, references, and iteration. Use it for non commercial research, workflow prototyping, and multi conditioning image pipelines.

View Model
FLUX.2 [flex]

FLUX.2 [flex]

FLUX.2 [flex] is a configurable text to image and image editing model built for precise text placement and stable layouts. It exposes sampling and guidance controls and supports up to ten reference images for consistent characters or products across complex compositions.

View Model
FLUX.1 Krea [dev]

FLUX.1 Krea [dev]

FLUX.1 Krea [dev] is an open‑weight text‑to‑image model from Black Forest Labs and Krea AI. It targets opinionated aesthetics and realistic photography. Developers can drop it into FLUX.1 dev workflows to build custom generators that avoid the typical AI look.

View Model
FLUX.1 Kontext [pro]

FLUX.1 Kontext [pro]

FLUX.1 Kontext [pro] combines fast text to image generation with precise image editing. It supports reference images, local region edits, and full scene changes while preserving style and character identity. Ideal for iterative workflows in design, product visuals, and storytelling pipelines.

View Model
FLUX.1 Kontext [max]

FLUX.1 Kontext [max]

FLUX.1 Kontext [max] is a high quality text to image model for production workflows. It focuses on prompt accuracy, sharp local edits, and premium typography rendering. Use it for detailed visual design, branded visuals, and consistent character safe image generation.

View Model
FLUX.1 Kontext [dev]

FLUX.1 Kontext [dev]

FLUX.1 Kontext [dev] is an open weights image editing model tuned for fast iterative development. It supports local edits and full scene changes from prompts. Use it for style transfer, background swaps, object edits, and character consistent variations in your pipelines.

View Model
FLUX.1 Expand [pro]

FLUX.1 Expand [pro]

FLUX.1 Expand [pro] is an outpainting model that extends images beyond their original frame while preserving structure, lighting, and style. It supports controlled expansion from real or generated inputs and integrates into image editing or generative workflows that need precise, coherent borders.

View Model
FLUX.1 Fill [dev]

FLUX.1 Fill [dev]

FLUX.1 Fill [dev] is an open image editing model for inpainting and outpainting with text guidance and masks. It can replace objects, extend scenes, and adjust regions while preserving context. Ideal for pipelines that need controllable edits on real or generated images.

View Model
FLUX.1 Canny [pro]

FLUX.1 Canny [pro]

FLUX.1 Canny Pro uses Canny edge maps as structural guidance. It lets you regenerate or transform images while preserving layout and contours. Ideal for style transfer, redesigns, and controlled edits where you must keep shapes consistent across outputs.

View Model
FLUX.1.1 [pro] Ultra

FLUX.1.1 [pro] Ultra

FLUX.1.1 [pro] Ultra is a high resolution text to image model from Black Forest Labs. It generates images up to 4 megapixels in about 10 seconds. Ultra mode targets sharp outputs. Raw mode targets natural photographic style. Built for API integration in real products.

View Model
FLUX.1 Depth [pro]

FLUX.1 Depth [pro]

FLUX.1 Depth [pro] uses depth maps to guide image generation and editing. It preserves 3D structure during transformations. Ideal for depth aware re-renders, camera moves, relighting, and layout constrained design workflows that need precise geometric consistency.

View Model
FLUX.1 Fill [pro]

FLUX.1 Fill [pro]

FLUX.1 Fill Pro provides advanced inpainting and outpainting for real and generated images. Supply an input image, mask, and text prompt. The model fills or extends regions with seamless content that matches context and style. Ideal for edits, layout fixes, and content-aware expansion.

View Model
FLUX.1 Canny [dev]

FLUX.1 Canny [dev]

FLUX.1 Canny [dev] is a 12B parameter rectified flow transformer for image generation. It takes a text prompt and an input image. It extracts canny edges as structural guidance. It then generates new images that follow the original composition while applying the prompt.

View Model
FLUX.1.1 [pro]

FLUX.1.1 [pro]

FLUX.1.1 Pro is a flagship text to image model from Black Forest Labs. It improves on FLUX.1 with sharper detail, stronger prompt adherence, and faster sampling. Ideal for production image pipelines, product visuals, and creative tools that require consistent high quality output.

View Model
FLUX.1 [pro]

FLUX.1 [pro]

FLUX.1 Pro is the flagship text to image model from Black Forest Labs. It targets production workflows that need strong prompt adherence, high visual quality, and diverse styles. Use it through the BFL API to generate robust images for design tools, apps, and creative pipelines.

View Model
FLUX.1 [dev]

FLUX.1 [dev]

FLUX.1 [dev] is a 12B parameter text to image model from Black Forest Labs. It targets high fidelity visual generation for research and non commercial use. Developers can build image apps that need strong prompt following and fine visual detail at high resolution.

View Model
FLUX.1 [schnell]

FLUX.1 [schnell]

FLUX.1 [schnell] is an open source text to image model from Black Forest Labs. It uses 4 step distillation for very fast generation with strong visual quality. Ideal for local deployment, rapid prototyping, batch image production, and integration into custom creative pipelines.

View Model
FLUX.1 Depth [dev]

FLUX.1 Depth [dev]

FLUX.1 Depth [dev] uses input depth maps as structural guidance for new image generation. It preserves scene geometry and layout while allowing creative control over style and details. Ideal for developers who need stable composition in controlled image synthesis.