Black Forest Labs · Photoreal images from a multimodal backbone.

FLUX 3

One model for all visual intelligence

FLUX 3 is Black Forest Labs' unified multimodal frontier model — image, video, audio and action from a single set of weights. Its Image mode targets photoreal detail, any style, and typographically accurate multilingual text.

4-in-1
Image, video, audio, action
Multilingual
In-image text rendering
20s
Native-audio video (same model)
2026
Announced July 23
What's new

One model for all visual intelligence

01

Unified multimodal core

Unlike FLUX.2, FLUX 3 learns jointly from images, video and audio in one architecture, then extends to action prediction. Image generation draws on that shared understanding rather than a separate image-only network.

02

Text that actually reads

FLUX 3 renders in-image text — signs, labels, posters, UI mockups — with far fewer garbled characters than prior FLUX and Stable Diffusion releases, including dense copy and non-Latin scripts.

03

Photoreal, any style

BFL positions FLUX 3 Image to close most of the remaining photorealism gap with Midjourney on skin texture, lighting and multi-subject scenes, while spanning illustration, product renders and fine art.

04

Self-Flow foundation

FLUX 3 is built on Self-Flow, BFL's flow-matching approach that aligns generation and understanding across modalities inside the same model.

Overview

Model at a glance

FLUX 3 is the third-generation flagship from Black Forest Labs (BFL), the Freiburg, Germany lab behind the FLUX family. Announced on 23 July 2026, it is a departure from its predecessors: rather than a standalone image model, FLUX 3 is a unified multimodal frontier model that jointly learns from images, video and audio within a single architecture and can be extended to predict actions. BFL frames it as a 'foundation layer for visual intelligence' — one network spanning image, video, audio and physical-AI action prediction, delivered across product lines including FLUX 3 Image, FLUX 3 Video, FLUX 3 Action and the upcoming open-weight FLUX 3 Dev.

This page focuses on FLUX 3's image capabilities. Because the model shares one backbone across modalities, image generation benefits from the same multimodal understanding used for video and audio, which BFL credits for stronger complex-prompt handling and markedly better in-image text rendering than FLUX.2. Note that FLUX 3 rolled out in phases: FLUX 3 Video and FLUX 3 Action opened in gated early access at launch, while FLUX 3 Image was announced as arriving 'in the coming weeks' and is only entering early access around early August 2026. As a result, some image-specific numbers (maximum resolution, parameter count) have not yet been officially published, and current image-quality claims come from BFL's own mid-training evaluations.

Model
FLUX 3 (Image mode)
Developer
Black Forest Labs
Announced
23 July 2026
Type
Unified multimodal flow model
Foundation
Self-Flow (flow matching)
Image availability
Early access, rolling out
Open weights
FLUX 3 Dev, later in 2026
Predecessor
FLUX.2
Capabilities

Key features

Shared multimodal understanding

FLUX 3 generates images from the same weights that model video and audio, so the image mode inherits a richer world model. BFL reports this yields better handling of complex, compositional prompts than FLUX.2's image-only design.

Accurate in-image text

One of FLUX 3's headline improvements is typography. It renders signs, labels, posters and UI copy with far fewer garbled characters, and extends to dense text blocks and non-Latin scripts — a long-standing weak point for diffusion image models.

Photoreal across styles

BFL positions FLUX 3 Image to hold up on skin texture, lighting and multi-subject scenes at a level closer to Midjourney, while remaining a generalist that spans photography, illustration, product renders and fine art.

Self-Flow architecture

FLUX 3 is built on Self-Flow, BFL's approach that combines a flow-matching objective with self-supervised feature reconstruction to align generation and understanding inside a single model. Self-Flow was first introduced by BFL in March 2026.

Flexible aspect ratios and resolutions

FLUX 3 Image is described as supporting a wide output range at flexible aspect ratios and resolutions, from square social crops to wide landscape formats, though exact maximum-resolution figures are not yet officially published for the image mode.

Part of a coordinated model family

Image, video, audio and action ship as product lines over one backbone, so a prompt style and understanding carry across modalities. An open-weight FLUX 3 Dev backbone is planned for later in 2026 for self-hosting and research.

Specs

Technical specifications

Model

NameFLUX 3 (Image mode)
DeveloperBlack Forest Labs (Freiburg, Germany)
Announced23 July 2026
Model typeUnified multimodal flow model
FoundationSelf-Flow (flow matching + self-supervised feature reconstruction)

Image capabilities

Modalities in one modelImage, video, audio, action
Text renderingMultilingual, including dense text and non-Latin scripts
Style rangePhotography, illustration, product renders, fine art
Aspect ratiosFlexible (square to wide landscape)
Max image resolutionNot yet officially published for FLUX 3 Image

Availability

FLUX 3 Video / ActionGated early access at launch
FLUX 3 ImageEntering early access (rolling out from ~Aug 2026)
FLUX 3 Dev (open weights)Planned later in 2026
SharkFotoComing soon
In practice

Use cases

Posters and marketing graphics

FLUX 3's stronger text rendering makes it well suited to layouts that need legible headlines, labels and body copy baked directly into the image, reducing manual retyping in an editor.

Product and e-commerce renders

Photoreal lighting and material handling support clean product shots and lifestyle scenes, with flexible aspect ratios for storefront, ad and social placements.

Concept art and illustration

The generalist style range spans illustration, fine art and stylised looks, giving artists and studios a single model for mood boards, key art and iteration.

Multilingual and localized visuals

Accurate rendering of non-Latin scripts helps teams create localized signage, packaging mockups and campaign assets across markets without swapping models.

UI and interface mockups

Cleaner rendering of UI labels and dense text makes FLUX 3 useful for early-stage app and web mockups where readable interface copy matters.

Generational leap

FLUX 3 vs FLUX.2

FLUX 3 is a fundamental shift from FLUX.2: where FLUX.2 was a 12B-parameter image-only model, FLUX 3 is a unified multimodal backbone. Note that FLUX 3 Image is still pre-general-availability, so several of its image specs are not yet officially confirmed.

FeatureFLUX.2FLUX 3NEW
ScopeImage generation onlyUnified image, video, audio and action
Architecture12B-param hybrid diffusion transformerSelf-Flow multimodal flow model
Native resolutionUp to 4K (3840x2160), 4MP nativeNot yet officially published for Image mode
In-image textStrong for a diffusion modelImproved multilingual accuracy, incl. non-Latin scripts
AvailabilityGenerally available (Pro/Flex/Dev)Phased early access; Image rolling out from ~Aug 2026
Honest look

Current limitations

Image mode still rolling out

At the 23 July 2026 launch, only FLUX 3 Video and FLUX 3 Action opened in early access. FLUX 3 Image is entering gated early access around August 2026, so broad, self-serve access may still be limited.

Image specs not fully published

BFL has not yet released official image-specific numbers such as maximum resolution or parameter count for FLUX 3 Image. Current image-quality claims are based partly on BFL's own mid-training evaluations rather than fully independent testing.

Open weights come later

The open-weight FLUX 3 Dev backbone is planned for later in 2026. Until then, self-hosting and offline fine-tuning of FLUX 3 are not available.

Multimodal, not image-first

FLUX 3 is engineered as a unified backbone where video prediction received the vast majority of training compute. Teams that want a dedicated, battle-tested image pipeline today may find FLUX.2 more predictable until FLUX 3 Image matures.

FAQ

Frequently asked questions

What is FLUX 3?
FLUX 3 is Black Forest Labs' third-generation flagship, announced on 23 July 2026. Unlike earlier FLUX releases, it is a unified multimodal frontier model that generates images, video and audio from one set of weights and can be extended to predict physical actions.
Is FLUX 3 an image model?
Not exclusively. FLUX 3 is a multimodal backbone, delivered across product lines including FLUX 3 Image, FLUX 3 Video, FLUX 3 Action and the open-weight FLUX 3 Dev. FLUX 3 Image is the image-generation mode of that shared model.
How is FLUX 3 different from FLUX.2?
FLUX.2 was an image-only model (12B parameters, native up to 4K). FLUX 3 is a unified multimodal architecture built on BFL's Self-Flow approach, with notably improved in-image text rendering and photorealism that BFL attributes to its shared multimodal understanding.
Can FLUX 3 render text in images?
Yes — improved text rendering is one of its headline features. FLUX 3 handles signs, labels, posters and UI copy with far fewer garbled characters than prior models, and supports dense text and non-Latin scripts.
Is FLUX 3 Image available yet?
It is rolling out. At launch, only FLUX 3 Video and FLUX 3 Action opened in gated early access. FLUX 3 Image was announced as arriving in the following weeks and is entering early access around early August 2026. FLUX 3 Dev open weights are planned for later in 2026.
What resolution does FLUX 3 Image produce?
Black Forest Labs has not yet officially published a maximum resolution for FLUX 3 Image, since it is still pre-general-availability. Its predecessor FLUX.2 generated natively up to 4K (3840x2160). We will update this page when official figures are confirmed.
Can I use FLUX 3 on SharkFoto?
FLUX 3 support on SharkFoto is coming soon. In the meantime you can use SharkFoto's currently available AI creative tools, and check back here for availability updates.

FLUX 3 is Coming to SharkFoto

We're adding FLUX 3 as platform access opens — explore SharkFoto's available AI tools today and check back for availability.

Try FLUX 3 now