Black Forest Labs Release Notes

For the first time a FLUX model will ship on consumer hardware. In partnership with ASUS and NVIDIA, creators picking up a new ASUS ProArt laptop will find FLUX.2 [klein] optimized for the device.

High-quality image generation, for a long time, usually means an API call. You need a connection, a backend, and latency. As of today, FLUX.2 [klein] 4B will ship preloaded in ASUS's MuseTree app on their next-generation ProArt laptop with RTX GPU lineup, which has debuted at Computex 2026 in Taipei.

Our target:

sub-5-second image generation on an 8GB VRAM laptop, while other pro apps are running in the background. No API or internet required; just the model, the hardware, and your creativity!

Why on-device, why now

Cloud inference is fast and flexible, but on-device changes what's possible for certain workflows. Privacy-sensitive use cases, offline work, low-latency iteration during a live session, are real constraints that real creators hit. ASUS's ProArt lineup is built for exactly that audience: photographers, video editors, designers who need compute that keeps pace with them.

FLUX.2 [klein] was already our fastest model by design, built for speed without compromising output quality. The latest advances in GPU performance open this up to use cases that weren't possible on consumer hardware before, and running it natively on RTX with NVIDIA's optimizations makes that real.

We're expanding our co-development partnerships to bring on-device FLUX to new form factors and workflows. If you're interested in shipping FLUX models optimized for your specific hardware or device, reach out to our team - let's build something together.

Partner with us

What if every shopper could see themselves in an outfit before buying? What if that experience ran fast, at catalog scale, with the garment rendered exactly as it exists?

That's what FLUX VTO is built for. Apparel runs on emotional selling, and try-on is the digital version of that moment when a shopper pictures themselves in the piece and decides they want it.

Why try-on has stayed stuck in the demo phase

Virtual try-on has been promised for years, but production deployments are rare. The reasons are familiar to anyone who has evaluated the category. Models drift between generations, so identity, hair and pose shift in ways that make outputs unusable on a live product page. Garments fare no better: logos disappear, stitching degrades, prints render incorrectly and buttons vanish. Even when the geometry is right, the look is often wrong, with outputs that don't match a brand's contrast, highlights or aesthetic.

And underneath all of that sits the economics problem. Existing try-on models take 10 to 30 seconds per generation, which is too slow for interactive shopping and too expensive to run across a full catalog.

Any one of these is enough to keep try-on out of production. Together they explain why so few catalogs have shipped it.

What FLUX VTO does differently

FLUX VTO is engineered for real shopping experiences, not demos. It clears the bar on the three dimensions retailers actually care about.

Speed and cost that work at catalog scale. Generations complete in under four seconds, fast enough to feel interactive in a consumer flow. The model is also cheaper to run than comparable systems, which is what makes try-on viable across thousands of SKUs rather than a curated handful.

Fidelity on both sides of the image. Identity is preserved across generations, and garments come through with their logos, prints, stitching and hardware intact. The output looks like the person wearing the actual product, not a reinterpretation of it.

Styling flexibility. Apply up to four garments to a single model at once, transfer full outfits or individual pieces between models, and layer items such as a shirt under a jacket with correct interaction between them.

What to know before you build with it

See the look, explore the fit. FLUX VTO shows how a garment looks on a person, making it easy to explore styling, silhouette, and overall fit. Precise body and garment sizing is still evolving, so outputs are best used as visual styling guidance.

Default moderation is on. Swimwear and lingerie are not supported under the default policy. Uploads must also follow standard safety guidelines: no adult-oriented content, no child sexual abuse imagery, no non-consensual or sexually explicit content and no dangerous, derogatory or shocking material.

Use rights matter. Only upload photos of yourself or photos where you have explicit rights to use the subject's likeness.

Need to run this even faster? You can also self-host the model and run the try-on in sub-second response time!

Go give it a try!

FLUX VTO is available publicly now. Check out the docs and try on some BFL Merch in our interactive and free to use BFL Shop Demo.

Also available in our FLUX MCP now!

A stray person in a product shot. A cable cutting through a landscape. Text baked into a scene. These are the types of details that can break an otherwise usable image, and correcting them manually takes a lot of time.

FLUX Erase removes whatever you mask - including its traces like shadows and subtle parts missed by the mask - and reconstructs the scene behind it coherently.

The problem with existing approaches

• Visible artifacts: most removal tools leave halos, smearing, or inconsistent texture at the edges of the removed area
• Incomplete reconstruction: the background fill is generated without understanding the full scene context, producing results that need manual correction
• Limited scope: tools trained narrowly on object removal struggle with text, people, watermarks, or compositionally complex scenes

FLUX Erase

Pass an image and a binary mask. The model erases whatever you've marked and reconstructs the scene behind it, matching lighting, texture, and background, no prompt required.

It works across objects, people, text, and anything else the mask defines. An optional edge expansion setting lets you expand the mask slightly for cleaner results on complex or soft-edged subjects.

FLUX Erase matches the quality of frontier object-removal models at a fraction of the price and latency.

We evaluated FLUX Erase against other state-of-the-art models on a held-out benchmark of 198 mask-based object-removal test images. FLUX Erase wins decisively against GPT Image-2 (68.5%) and Finegrain Eraser Standard (63.2%), ties Nano Banana 2 (49.5%), and lands closely behind Nano Banana Pro (47.3%) - putting it on par with the current frontier of mask-based object-removal while running lightning fast and at a substantially lower cost.

Get access

Try the public demo.

FLUX Erase is available via the BFL API.

View docs.

View Pricing.

Expanding an image beyond its original frame is harder than it should be.

Most outpainting tools today still give you visible seams, broken lighting, or loss of context. We built FLUX Outpainting to solve this, and you can try it now.

The problem with existing approaches

• Seams and artifacts: most outpainting tools produce visible boundaries where the generated content meets the original (inconsistent lighting, broken edges, mismatched texture)
• Prompt dependency: models that require detailed text prompts to expand a scene introduce extra steps and unpredictable outputs
• Rigid formats: changing an image's aspect ratio means rebuilding content rather than extending it

FLUX Outpainting

FLUX Outpainting is a purpose-built expansion endpoint. Pass an image, define your target canvas size and placement, and get back a seamlessly extended result: coherent, photorealistic, and ready to use.

What makes it different:

• Natural scene extension: the model is optimized for visually coherent continuation, carrying lighting, texture, depth, and composition through without instruction
• Flexible canvas control: define the full output dimensions and image placement coordinates directly, maps cleanly to canvas-based UIs and integrates straight into the API
• Up to 4MP output: full-resolution results, ready for production

Get access

FLUX Outpainting is available via the BFL API.

Try the public demo.

View API Docs

View Pricing

Black Forest Labs is pushing the frontier of visual intelligence. Our team has released some of the most capable and most popular AI models globally. As we grow, we're taking steps to combat misuse, protect the community, and show that high performance, open innovation, and sensible safeguards go hand in hand. Today, we're excited to share early results that help validate our mitigations for emerging risks—including synthetic non-consensual intimate imagery (NCII) and child sexual abuse material (CSAM)—and will help us strengthen these safeguards in the future.

• On third-party evaluations, our latest FLUX.2 model family demonstrates strong >10 times fewer vulnerabilities for serious risks than other leading open-weight image models, including those from large technology firms.
• Our targeted post-training mitigations help to reduce vulnerabilities by 77-98% prior to release.
• Alongside other safeguards, these mitigations can meaningfully reduce the risk of widespread misuse. For example, industry-standard moderation practices during deployment can eliminate most, if not all, residual vulnerabilities for NCII and CSAM.

Black Forest Labs is committed to open innovation

Black Forest Labs is committed to open research and development as the bedrock for competition, innovation, and security in AI. By sharing our research breakthroughs openly, we can help to accelerate the discovery of new techniques, methods, and architectures. By sharing our models openly, we enable developers around the world to build new tools that we can scarcely imagine today—from kitchen table startups to the world’s largest enterprises. To date, our founding team has contributed three of the four most popular open-weight AI models on Hugging Face, totaling over 400 million downloads. Today, our FLUX family leads the most capable open-weight image models.

We face unique challenges

We face unique challenges We take our responsibility to mitigate emerging risks seriously. The properties that make open-weight models useful can also pose a unique challenge for risk management. These models can be deployed independently without oversight from the original developer and without appropriate safeguards, in some cases using consumer hardware. They can be modified or integrated with other systems for unauthorized purposes. If a vulnerability is discovered after release, it is not possible to fully withdraw all copies of the affected model.

We respond with layers of mitigation

We respond with layers of mitigation While there are no silver bullets to prevent all misuse, layers of mitigation can help to prevent widespread misuse. Before each release, we evaluate a number of risks, including the production of unlawful content, with a focus on synthetic NCII and CSAM. We implement a series of pre-release mitigations in our models to help prevent misuse, with other post-release safeguards to address residual vulnerabilities. These mitigations incorporate best practices outlined by nonprofit organizations such as Thorn as well as agencies such as the US National Institute of Standards and Technology and the UK Office of Communications.

1. Pre-training. We filter pre-training data for multiple categories of nude and pornographic material and known CSAM. Limiting exposure to this data in the first place can help prevent a user generating unlawful content, whether by eliciting harmful features in the data, or by combining lawful features into an unlawful composite image. We have partnered with the Internet Watch Foundation, an independent nonprofit organization dedicated to preventing online abuse, to filter known CSAM from the training data.
2. Post-training. We undertake multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse, spanning both text-to-image (T2I) and image-to-image (I2I) attacks. By suppressing certain concepts in the trained model, these techniques can help prevent a user generating synthetic NCII or CSAM from a text prompt, or transforming an uploaded image into synthetic NCII or CSAM.
3. Deployment. We release our most capable open-weight models with enforceable licenses that prohibit unlawful or infringing misuse, and require the use of filters during inference. With our open-weight models, we provide filters to help deployers detect violative or infringing activity. On our hosted services, we implement filters for a range of content types—including sexual content, hate, violence and gore, and representations of self-harm—and maintain a reporting relationship with the U.S. National Center for Missing and Exploited Children. Additionally, we apply content provenance metadata on our hosted services to help platforms and viewers identify AI-generated content once it is shared online. We include links to the Coalition for Content Provenance and Authenticity (C2PA) in our open-weight repositories to help other developers implement this metadata.
4. After deployment. We subsequently monitor for patterns of violative use in both our hosted services and the open developer community. We issue and escalate takedown requests to websites, services, or businesses that misuse our models. Additionally, we may ban users or developers we detect violating our policies. We provide a dedicated email hotline to solicit feedback from the community, and welcome ongoing engagement with authorities, developers, and researchers to share intelligence about emerging risks and effective mitigations.

Throughout the development lifecycle, we conduct multiple internal and external evaluations to identify further opportunities for mitigation. For our latest open-weight model family, FLUX.2, we partnered with Cinder to conduct third-party red-teaming prior to each of our five open-weight model releases. These included FLUX.2 [dev]—a 32 billion parameter model based on rectified flow transformer architecture that enables high-quality image generation and editing—and FLUX.2 [klein], a derivative series of four size-distilled and step-distilled models, ranging from 4 to 9 billion parameters, optimized for local deployment, faster inference, and improved photorealism.

Third-party testing informed our release decision

Third-party testing informed our release decision Prior to release, we tasked Cinder to evaluate these models throughout their development lifecycle, including early, intermediate, and final checkpoints. These evaluations focused on identifying CSAM and NCII vulnerabilities across a range of T2I and I2I attacks. By observing the models’ behavior before, during, and after fine-tuning and distillation, we could better refine our mitigation strategy and make a considered release decision. We also instructed Cinder to run the same evaluation on leading open-weight models from other firms to help assess the marginal risk of our releases compared to the baseline.

Attacks included prompts that:

• Directly attempt to elicit violative content;
• Obscure a violative request in an otherwise benign context;
• Obfuscate intent through indirect language, “l33t”, or scrambling;
• Attempt to construct a violative image by assembling features that are individually nonviolative; and
• Request analogous visual features or substitutes in place of violative terms.

For I2I evaluations, which included one or more input images, attacks included requests to:

• Undress, simulate, or reimagine an otherwise clothed individual;
• De-age an individual;
• Splice together multiple individuals to produce a violative composite figure; and
• Merge multiple images into a violative scene.

Human labelers were instructed to classify outputs as potential NCII based on a range of factors, including whether an individual in the output image was depicted in a state of undress and whether they were still identifiable from the prompt, input images, or general knowledge. They were instructed to classify outputs as potential CSAM based on age, nudity anywhere in frame, and other sexual, suggestive, abusive, or obscene features, consistent with legal definitions of CSAM. Additionally, labelers were asked to characterize the model’s defensive response—such as whether the model ignored the prompt, cropped the image, or obscured violative features—to help refine our fine-tuning approach.

Our models demonstrate 10x fewer vulnerabilities

Our models demonstrate 10x fewer vulnerabilities Totaling nearly 4,000 prompts, these evaluations yielded a rich picture of comparative risk that helped inform our release decision:

1. Comparative risk. Our five models demonstrated over 10 times fewer vulnerabilities than other popular open-weight models, indicating a higher robustness to misuse. These include models recently developed or funded by large technology firms with substantial resources, such as Alibaba, Tencent, and ByteDance.
2. Progressive mitigation. Our post-training mitigations yielded a 77-98 percent reduction in vulnerabilities compared to earlier checkpoints. Importantly, our most lightweight and efficient [klein] models—those likely to experience the widest adoption for local inference—demonstrated the fewest vulnerabilities.
3. Residual vulnerabilities. Subsequent evaluations with Cinder suggested that residual vulnerabilities can be nearly eliminated in deployment through the adoption of industry-standard moderation practices.

Above. Violative rates across popular open-weight models compared to the most vulnerable model evaluated (Hunyuan Image 3.0). Released Black Forest Labs models in dark green. n≈3,800 prompts, covering both T2I and I2I, NCII and CSAM attacks. Outputs were classified by human labelers. Models or model families capable of T2I and I2I were evaluated for both types of attack, else they were evaluated on a single modality only. Relative performance indicated by text-to-image Elo ratings (a measure of general performance; February 2026).

We subsequently decided to release FLUX.2 [dev], FLUX.2 [klein] 9B Base, and FLUX.2 [klein] 9B under a non-commercial open-weight license that permits free use for personal and research applications, and FLUX.2 [klein] 4B Base and FLUX.2 [klein] 4B under an Apache 2.0 license.

Limitations

Limitations This evaluation could not directly measure robustness to adversarial modification (e.g. via fine-tuning or low rank adapters (LoRAs). However, we expect that circumventing our embedded mitigations will be more challenging than with other models. These safeguards should raise the expertise, data, and compute barrier to a malicious actor introducing unsafe behaviors to the model. Additionally, popular platforms like Hugging Face and CivitAI continue to improve their moderation of unlawful or violative repositories, such as LoRAs intended to produce NCII. Together, we expect that embedded mitigations in our models coupled with robust downstream moderation will help to significantly reduce the distribution of malicious derivative models and unlawful content online.

This is just the beginning, and we are constantly improving

This is just the beginning, and we are constantly improving We are a small team with global impact, and the only European and American lab releasing frontier open-weight models for visual generation. Our models compete with China’s largest technology firms. Yet despite significant risk mitigation, our models continue to rank among the most capable and most popular. Through our collaboration with Cinder, we have shown that performance, openness, and safety are not mutually exclusive.

These are early days, and we are constantly improving. We welcome ongoing dialogue with researchers, authorities, and developers as we continue to refine our approach to these risks. Please reach out to us at [email protected] with feedback!

—Black Forest Labs

Today, we release the FLUX.2 [klein] model family, our fastest image models to date.

FLUX.2 [klein] unifies generation and editing in a single compact architecture, delivering state-of-the-art quality with end-to-end inference as low as under a second. Built for applications that require real-time image generation without sacrificing quality, and runs on consumer hardware with as little as 13GB VRAM.

Try it now for free here

Demo showing editing with FLUX.2 [klein]

Why go [klein]?

Visual Intelligence is entering a new era. As AI agents become more capable, they need visual generation that can keep up; models that respond in real-time, iterate quickly, and run efficiently on accessible hardware.

The klein name comes from the German word for "small", reflecting both the compact model size and the minimal latency. But FLUX.2 [klein] is anything but limited. These models deliver exceptional performance in text-to-image generation, image editing and multi-reference generation, typically reserved for much larger models.

What's New

• Sub-second inference. Generate or edit images in under 0.5s on modern hardware.
• Photorealistic outputs and high diversity, especially in the base variants.
• Unified generation and editing. Text-to-image, image editing, and multi-reference support in a single model while delivering frontier performance.
• Runs on consumer GPUs. The 4B model fits in ~13GB VRAM (RTX 3090/4070 and above).
• Developer-friendly & Accessible: Apache 2.0 on 4B models, open weights for 9B models. Full open weights for customization and fine-tuning.
• API and open weights. Production-ready API or run locally with full weights.

Note: The “FLUX [dev] Non-Commercial License” has been renamed to “FLUX Non-Commercial License” and will apply to the 9B Klein models. No material changes have been made to the license.

Text to Image collage using FLUX.2 [klein]

The FLUX.2 [klein] Model Family

FLUX.2 [klein] 9B

Our flagship small model. Defines the Pareto frontier for quality vs. latency across text-to-image, single-reference editing, and multi-reference generation. Matches or exceeds models 5x its size - in under half a second. Built on a 9B flow model with 8B Qwen3 text embedder, step-distilled to 4 inference steps.

Combine multiple input images, blend concepts, and iterate on complex compositions - all at sub-second speed with frontier-level quality. No model this fast has ever done this well.

License: FLUX NCL

Imagine editing collage using FLUX.2 [klein]

FLUX.2 [klein] 4B:

Fully open under Apache 2.0. Our most accessible model, it runs on consumer GPUs like the RTX 3090/4070. Compact but capable: supports T2I, I2I, and multi-reference at quality that punches above its size. Built for local development and edge deployment.

License: Apache 2.0

FLUX.2 [klein] Base 9B / 4B:

The full-capacity foundation models. Undistilled, preserving complete training signal for maximum flexibility. Ideal for fine-tuning, LoRA training, research, and custom pipelines where control matters more than speed. Higher output diversity than the distilled models.

License: 4B Base under Apache 2.0, 9B Base under FLUX NCL

Output Diversity using FLUX.2 [klein]

Quantized versions

We are also releasing FP8 and NVFP4 versions of all [klein] variants, developed in collaboration with NVIDIA for optimized inference on RTX GPUs. Same capabilities, smaller footprint - compatible with even more hardware.

• FP8: Up to 1.6x faster, up to 40% less VRAM
• NVFP4: Up to 2.7x faster, up to 55% less VRAM

Benchmarks on RTX 5080/5090, T2I at 1024×1024

Same licenses apply: Apache 2.0 for 4B variants, FLUX NCL for 9B.

Performance Analysis

FLUX.2 [klein] Elo vs Latency (top) and VRAM (bottom) across Text-to-Image, Image-to-Image Single Reference, and Multi-Reference tasks.

FLUX.2 [klein] matches or exceeds Qwen's quality at a fraction of the latency and VRAM, and outperforms Z-Image while supporting both text-to-image generation and (multi-reference) image editing in a unified model. The base variants trade some speed for full customizability and fine-tuning, making them better suited for research and adaptation to specific use cases. Speed is measured on a GB200 in bf16.

Into the New

FLUX.2 [klein] is more than a faster model. It's a step toward our vision of interactive visual intelligence. We believe the future belongs to creators and developers with AI that can see, create, and iterate in real-time. Systems that enable new categories of applications: real-time design tools, agentic visual reasoning, interactive content creation.

Resources

Try it

• Demo
• Playground
• HF Space for [klein] 9B, HF Space for [klein] 4B

Build with it

• Documentation
• GitHub
• Model Weights

Learn more

• https://bfl.ai/models/flux-2-klein

FLUX.2 is designed for real-world creative workflows, not just demos or party tricks. It generates high-quality images while maintaining character and style consistency across multiple reference images, following structured prompts, reading and writing complex text, adhering to brand guidelines, and reliably handling lighting, layouts, and logos. FLUX.2 can edit images at up to 4 megapixels while preserving detail and coherence.

Black Forest Labs: Open Core

We believe visual intelligence should be shaped by researchers, creatives, and developers everywhere, not just a few. That’s why we pair frontier capability with open research and open innovation, releasing powerful, inspectable, and composable open-weight models for the community, alongside robust, production-ready endpoints for teams that need scale, reliability, and customization.

When we launched Black Forest Labs in 2024, we set out to make open innovation sustainable, building on our experience developing some of the world’s most popular open models. We’ve combined open models like FLUX.1 [dev]—the most popular open image model globally—with professional-grade models like FLUX.1 Kontext [pro], which powers teams from Adobe to Meta and beyond. Our open core approach drives experimentation, invites scrutiny, lowers costs, and ensures that we can keep sharing open technology from the Black Forest and the Bay into the world.

From FLUX.1 to FLUX.2

Precision, efficiency, control, extreme realism - where FLUX.1 showed the potential of media models as powerful creative tools, FLUX.2 shows how frontier capability can transform production workflows. By radically changing the economics of generation, FLUX.2 will become an indispensable part of our creative infrastructure.

Output Versatility: FLUX.2 is capable of generating highly detailed, photoreal images along with infographics with complex typography, all at resolutions up to 4MP

What’s New

• Multi-Reference Support: Reference up to 10 images simultaneously with the best character / product / style consistency available today.
• Image Detail & Photorealism: Greater detail, sharper textures, and more stable lighting suitable for product shots, visualization, and photography-like use cases.
• Text Rendering: Complex typography, infographics, memes and UI mockups with legible fine text now work reliably in production.
• Enhanced Prompt Following: Improved adherence to complex, structured instructions, including multi-part prompts and compositional constraints.
• World Knowledge: Significantly more grounded in real-world knowledge, lighting, and spatial logic, resulting in more coherent scenes with expected behavior.
• Higher Resolution & Flexible Input/Output Ratios: Image editing on resolutions up to 4MP.

All variants of FLUX.2 offer image editing from text and multiple references in one model.

Available Now

The FLUX.2 family covers a spectrum of model products, from fully managed, production-ready APIs to open-weight checkpoints developers can run themselves. The overview graph below shows how FLUX.2 [pro], FLUX.2 [flex], FLUX.2 [dev], and FLUX.2 [klein] balance performance, and control

• FLUX.2 [pro]: State-of-the-art image quality that rivals the best closed models, matching other models for prompt adherence and visual fidelity while generating images faster and at lower cost. No compromise between speed and quality. → Available now at BFL Playground, the BFL API and via our launch partners.
• FLUX.2 [flex]: Take control over model parameters such as the number of steps and the guidance scale, giving developers full control over quality, prompt adherence and speed. This model excels at rendering text and fine details. → Available now at bfl.ai/play, the BFL API and via our launch partners.
• FLUX.2 [dev]: 32B open-weight model, derived from the FLUX.2 base model. The most powerful open-weight image generation and editing model available today, combining text-to-image synthesis and image editing with multiple input images in a single checkpoint. FLUX.2 [dev] weights are available on Hugging Face and can now be used locally using our reference inference code. On consumer grade GPUs like GeForce RTX GPUs you can use an optimized fp8 reference implementation of FLUX.2 [dev], created in collaboration with NVIDIA and ComfyUI. You can also sample Flux.2 [dev] via API endpoints on FAL, Replicate, Runware, Verda, TogetherAI, Cloudflare, DeepInfra. For a commercial license, visit our website.
• FLUX.2 [klein] (coming soon): Open-source, Apache 2.0 model, size-distilled from the FLUX.2 base model. More powerful & developer-friendly than comparable models of the same size trained from scratch, with many of the same capabilities as its teacher model. Join the beta
• FLUX.2 - VAE: A new variational autoencoder for latent representations that provide an optimized trade-off between learnability, quality and compression rate. This model provides the foundation for all FLUX.2 flow backbones, and an in-depth report describing its technical properties is available here. The FLUX.2 - VAE is available on HF under an Apache 2.0 license.

Generating designs with variable steps: FLUX.2 [flex] provides a “steps” parameter, trading off typography accuracy and latency. From left to right: 6 steps, 20 steps, 50 steps.

Controlling image detail with variable steps: FLUX.2 [flex] provides a “steps” parameter, trading off image detail and latency. From left to right: 6 steps, 20 steps, 50 steps.

The FLUX.2 model family delivers state-of-the-art image generation quality at extremely competitive prices, offering the best value across performance tiers.

For open-weights image models, FLUX.2 [dev] sets a new standard, achieving leading performance across text-to-image generation, single-reference editing, and multi-reference editing, consistently outperforming all open-weights alternatives by a significant margin.

Whether open or closed, we are committed to the responsible development of these models and services before, during, and after every release.

How It Works

FLUX.2 builds on a latent flow matching architecture, and combines image generation and editing in a single architecture. The model couples the Mistral-3 24B parameter vision-language model with a rectified flow transformer. The VLM brings real world knowledge and contextual understanding, while the transformer captures spatial relationships, material properties, and compositional logic that earlier architectures could not render.

FLUX.2 now provides multi-reference support, with the ability to combine up to 10 images into a novel output, an output resolution of up to 4MP, substantially better prompt adherence and world knowledge, and significantly improved typography. We re-trained the model’s latent space from scratch to achieve better learnability and higher image quality at the same time, a step towards solving the “Learnability-Quality-Compression” trilemma. Technical details can be found in the FLUX.2 VAE blog post.

More Resources:

• FLUX.2 Documentation
• FLUX.2 Prompting Guide
• FLUX.2 Open Weights / Inference Code
• FLUX Playground

Into the New

We're building foundational infrastructure for visual intelligence, technology that transforms how the world is seen and understood. FLUX.2 is a step closer to multimodal models that unify perception, generation, memory, and reasoning, in an open and transparent way.

Join us on this journey. We're hiring in Freiburg (HQ) and San Francisco. View open roles.

Until now, testing different generative models meant juggling apps, exporting files, and piecing results together. With FLUX.1 Kontext [Pro] inside Photoshop, that friction disappears. You can select our model, simply describe the edits you want, then refine them with Photoshop’s suite of tools. That leads to precise and coherent results, while maintaining your full creative control.

Starting September 25th, Photoshop (beta) users around the world will be able to use FLUX.1 Kontext [Pro] directly inside Generative Fill, and for a limited time during beta, users can try out our model for free.

Our models are built on the frontier of generative visual AI research. FLUX.1 Kontext [Pro] doesn’t just deliver contextual accuracy and creative flexibility, it’s 3X faster than competing models, making the experience significantly more seamless. That means less waiting, more iterating, and more time spent in flow.

• Photographers: Select a subject and let FLUX.1 Kontext [Pro] generate contextually accurate backgrounds that blend seamlessly, while Photoshop’s masking keeps your subject untouched.
• Designers: Add realistic props, signage, or scenery into layouts. FLUX.1 Kontext [Pro]’s fills integrate naturally, and Photoshop’s blending modes and smart objects ensure polish.
• Creative Directors: Mock up campaign assets or product shots at speed. Generate consistent, on-brand details with FLUX.1 Kontext [Pro], then perfect them using Photoshop’s adjustments.

By pairing Photoshop’s professional editing environment with FLUX.1 Kontext [Pro]’s accuracy and unmatched speed, creators everywhere gain the freedom to push imagination further. We’re bringing our vision: to power every pixel, everywhere, directly into your daily workflow.

Get started now

Starting today, Black Forest Labs’ flagship models are available directly from Microsoft on Azure AI Foundry.

FLUX.1 Kontext [pro] and FLUX1.1 [pro] can be accessed through Azure AI Foundry, offering customers an enterprise-ready path to deploy our state-of-the-art text-to-image and image-to-image foundation models with the scale, security, and simplicity of Azure.

BFL’s collaboration with Microsoft started from our earliest days when we partnered with Azure to build our training and inference clusters. Since then, we’ve worked hand in hand with Microsoft to optimize our model performance and make it easier for customers to access our models. Today, everything from exploration to deployment of our models becomes faster with FLUX.1 Kontext [pro] and FLUX.1.1 [pro] available through Azure’s powerful ecosystem.

Why this matters

With FLUX models now on Azure, you get:

• Microsoft-backed Service Level Agreements
• Azure-native deployment and observability
• Access via pay-as-you-go or Provisioned Throughput (fungible PTUs), meaning you can flexibly use your quota and reservations across any Direct from Azure models.
• Adherence to Microsoft's Responsible AI standards
• Enterprise security, governance, and scalability
• Zero compromise in speed and quality

What you can build

FLUX.1 Kontext [pro] offers the in-context image generation and iterative editing capabilities, allowing with a single model for you to make local edits, transfer styles, replace background, add typography - all while retaining character consistency and offering up to 8x the speed of other editing models for 1MP resolution. On KontextBench, FLUX.1 Kontext [pro] ranks #1 on text-guided editing and character-consistency.

FLUX1.1 [pro] is another lightning fast text-to-image model that offers up to 1.6MP resolution.

Whether you’re:

• An e-commerce company looking to integrate our models for product photography,
• A financial services company looking to streamline marketing materials, or
• A studio wanting to consistently build out a visual story

you can deploy our FLUX models directly from Azure AI Foundry with the convenience of working through your Azure account.

Get started on Azure AI Foundry by doing the following:

• If you don’t have an Azure subscription, you can sign up for an Azure account here.
• Navigate to Azure AI Foundry at ai.azure.com
• Search the model name, e.g. “FLUX Kontext” for image editing, or "Flux 1.1", for text to image, in the model catalog
• Open the model card in the model catalog on Azure AI Foundry.
• Click on “deploy” to obtain the inference API and key and also to access the playground.
• You should land on the deployment page that shows you the API and key in less than a minute. You can try out your prompts in the playground.
• You can use the API and key with various clients

We can’t wait to see what you create.

An ‘Opinionated’ Text-to-Image Model

The BFL model garden just got an exciting update: We are proud to release FLUX.1 Krea [dev], developed in collaboration with Krea AI. FLUX.1 Krea [dev] is a new state-of-the-art open-weights model for text-to-image generation that overcomes the oversaturated 'AI look' to achieve new levels of photorealism with its distinctive aesthetic approach.

FLUX.1 Krea [dev] is the open weights version of Krea 1, offering strong performance with highly distinctive aesthetics and exceptional realism. It has been trained with the goal to generate more realistic and diverse images that do not contain oversaturated textures, a known issue in text-to-image generation. Due to these properties, we call FLUX.1 Krea [dev] ‘opinionated’ - a text-to-image model that offers its users pleasant surprises in the form of diverse, visually interesting images.

Despite its idiosyncrasies, FLUX.1 Krea [dev] outperforms previous open text-to-image models and is on par with closed solutions like FLUX1.1 [pro] in human preference assessments. Moreover it is architecturally compatible with the FLUX.1 [dev] ecosystem and serves as a flexible base model for customization for down-stream applications.

The weights of FLUX.1 Krea [dev] are now available in the BFL HuggingFace repository. Commercial Licenses can are available in the BFL Licensing Portal. Our partners FAL, Replicate, Runware, DataCrunch and TogetherAI provide API endpoints for easy integration.

Key Features of FLUX.1 Krea [dev]

The key features of our most recent open-weights text-to-image model are

• State-of-the-art open text-to-image generation
• Highly distinctive aesthetics that overcome the common "AI look" problem
• Exceptional realism and image quality
• Enhanced flexibility for customization
• Compatibility with the FLUX.1 [dev] architecture and ecosystem

Collaborative Model Development

This joint project between BFL and Krea demonstrates the value of collaborative model development between foundation model and applied AI labs. By providing a specialized and flexible base model tailored for down-stream finetuning, we helped Krea to achieve previously unfeasible results.

FLUX.1 Krea [dev] showcases how targeted collaboration between foundation model developers and application-focused teams can push the boundaries of open AI image generation.

We're just getting started. If you want to join us on our mission, we are actively hiring talented individuals across multiple roles. Apply here.

Up until today, all capable generative image editing models were only available as proprietary tools. Today, that changes. We release FLUX.1 Kontext [dev], our developer version of FLUX.1 Kontext [pro], which delivers proprietary-level image editing performance in a 12B parameter model that can run on consumer hardware.

Making model weights openly accessible is fundamental to technological innovation. FLUX.1 Kontext [dev] is now available as an open-weight model under the FLUX.1 Non-Commercial License, providing free access for research and non-commercial use. FLUX.1 Kontext [dev] is compatible with the existing FLUX.1 [dev] inference code and comes with day-0 support for popular inference frameworks like ComfyUI, HuggingFace Diffusers and TensorRT.

The model weights are available on HuggingFace. Our partners FAL, Replicate, Runware, DataCrunch and TogetherAI and ComfyUI provide ready-to-use API endpoints and code for cloud-based and/or local inference.

The technical report is available on arxiv.

Setting New Standards in Open Image Editing

FLUX.1 Kontext [dev] focuses exclusively on editing tasks. The model enables iterative editing, excels at character preservation across a diverse set of scenes and environments, and allows both precise local and global edits.

At Black Forest Labs, we remain committed to providing researchers and developers with best-in-class open tools that are competitive with existing proprietary solutions. To validate the performance of FLUX.1 Kontext [dev], we conducted extensive evaluation across multiple image editing benchmarks.

Human preference evaluations on KontextBench, our newly released image editing benchmark, demonstrate that FLUX.1 Kontext [dev] outperforms existing open image editing models, (Bytedance Bagel, HiDream-E1-Full) and closed models (Google's Gemini-Flash Image) across many categories. Independent evaluations run by Artificial Analysis confirm these findings.

Optimized for NVIDIA Blackwell Architecture

We have collaborated with NVIDIA to build optimized TensorRT weights specifically designed for the new NVIDIA Blackwell architecture which brings greatly improved inference speed and reduces memory usage while maintaining high-quality image editing performance.

Additionally to the original FLUX.1 Kontext [dev] weights, we’re making available these BF16, FP8 and FP4 TensorRT variants in our Hugging Face repository, giving developers the flexibility to balance speed, efficiency, and quality tailored to their use case. These optimized weights ensure that FLUX.1 Kontext [dev] can take full advantage of the latest hardware capabilities.

Streamlined Commercial Access: The BFL Self-Serve Portal

We are releasing a self-serve licensing portal with transparent terms and standardized commercials for simplifying commercial access to all of our open weights models. This includes the novel FLUX.1 Kontext [dev] as well as the FLUX.1 Tools [dev] and the popular text-to-image model FLUX.1 [dev].

Our self-serve portal provides transparent licensing terms that enable businesses to confidently integrate FLUX.1 models into their commercial products and services. Commercial Licenses to our open weights models can now be purchased with only a few clicks, accelerating the path from development to deployment. More information on self-serve licensing can be found at the BFL Helpdesk.

License Update

Black Forest Labs also updated the FLUX.1 [dev] Non-Commercial License with the following changes:

1. Non-Commercial Purpose. We edited the definition of “Non-Commercial Purpose” to better clarify what constitutes Non-Commercial Purposes under the FLUX.1 [dev] Non-Commercial License.
2. Content Filters. To prevent the creation and dissemination of unlawful or infringing content, the FLUX.1 [dev] Non-Commercial License requires content filters or manual review to be used with the FLUX.1 [dev] models. We’ve also made corresponding adjustments to the indemnification of the license.
3. Content Provenance. Users of FLUX.1 [dev] Models under a FLUX.1 [dev] Non-Commercial License must follow applicable law for content provenance under the license.
4. Restrictions. We made some clarifications on what are not permitted uses of FLUX.1 [dev] Models under a FLUX.1 [dev] Non-Commercial License.

Resources

• Model weights: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev
• Code: https://github.com/black-forest-labs/flux
• API Documentation: https://docs.bfl.ai/quick_start/introduction
• Self-Serve Portal: http://bfl.ai/pricing/licensing
• Helpdesk: https://help.bfl.ai

We're just getting started. If you want to join us on our mission, we are actively hiring talented individuals across multiple roles. Apply here.

Today, we are excited to release FLUX.1 Kontext, a suite of generative flow matching models that allows you to generate and edit images.

Unlike existing text-to-image models, the FLUX.1 Kontext family performs in-context image generation, allowing you to prompt with both text and images, and seamlessly extract and modify visual concepts to produce new, coherent renderings.

Consistent, context-aware text-and-image generation and editing.

YOUR IMAGES. YOUR WORDS. YOUR WORLD.

FLUX.1 Kontext marks a significant expansion of classic text-to-image models by unifying instant text-based image editing and text-to-image generation. As a multimodal flow model, it combines state-of-the-art character consistency, context understanding and local editing capabilities with strong text-to-image synthesis.

Improved Text-to-Image Capabilities

Whether for ideation, drafting, conceptual design, or just for fun - text-to-image remains a crucial component of today's image generation. The FLUX.1 Kontext models deliver state-of-the-art image generation results with strong prompt following, photorealistic rendering, and competitive typography—all at inference speeds up to 8x faster than current leading models (e.g. GPT-Image).

Play. Create. Manipulate…

FLUX.1 Kontext models go beyond text-to-image. Unlike previous flow models that only allow for pure text based generation, FLUX.1 Kontext models also understand and can create from existing images. With FLUX.1 Kontext you can modify an input image via simple text instructions, enabling flexible and instant image editing - no need for finetuning or complex editing workflows. The core capabilities of the the FLUX.1 Kontext suite are:

• 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: Make targeted modifications of specific elements in an image without affecting the rest.
• Style Reference: Generate novel scenes while preserving unique styles from a reference image, directed by text prompts.
• Interactive Speed: Minimal latency for both image generation and editing.

…and Iterate: modify step by step

Flux.1 Kontext allows you to iteratively add more instructions and build on previous edits, refining your creation step-by-step with minimal latency, while preserving image quality and character consistency.

The FLUX.1 Kontext [pro] Models

As part of the FLUX.1 Kontext suite we bring two new in-context image models to the BFL API.

• FLUX.1 Kontext [pro] - A pioneer for fast, iterative image editing

A single model that delivers local editing, generative in-context modifications and classic text-to-image generation in signature FLUX.1 quality. FLUX.1 Kontext [pro] handles both text and reference images as inputs, seamlessly enabling targeted, local edits in specific image regions and complex transformations of entire scenes. Operating up to an order of magnitude faster than previous state-of-the art models, FLUX.1 Kontext [pro] is a pioneer for iterative editing, since it’s the first model that allows users to build upon previous edits through multiple turns, while maintaining characters, identities, styles, and distinctive features consistent across different scenes and viewpoints.

• FLUX.1 Kontext [max] - Maximum Performance at High SpeedOur new experimental model greatly improves prompt adherence and typography generation, and high consistency for editing. All these without compromise on speed.

FLUX.1 Kontext [max] and FLUX.1 Kontext [pro] are available at KreaAI, Freepik, Lightricks, OpenArt, and LeonardoAI and via our infrastructure partners FAL, Replicate, Runware, DataCrunch, TogetherAI and ComfyOrg. We received support for preference data collection by OpenArt and KreaAI.

FLUX.1 Kontext [dev] available in Private Beta

We deeply believe that open research and weight sharing are fundamental to safe technological innovation. We developed an open-weight variant, FLUX.1 Kontext [dev] - a lightweight 12B diffusion transformer suitable for customization and compatible with previous FLUX.1 [dev] inference code. We open FLUX.1 Kontext [dev] in a private beta release, for research usage and safety testing. Please contact us at [email protected] if you’re interested. Upon public release FLUX.1 Kontext [dev] will be distributed through our partners FAL, Replicate, Runware, DataCrunch, TogetherAI and HuggingFace.

Performance Evaluation

To validate the performance of our FLUX.1 Kontext models we conducted an extensive performance evaluation that we release in a tech report. Here we give a short summary: to evaluate our models, we compile KontextBench, a benchmark for text-to-image generation and image-to-image generation from crowd-sourced real-world use cases. We will release this benchmark in the future.

We show evaluation results across six in-context image generation tasks. FLUX.1 Kontext [pro] consistently ranks among the top performers across all tasks, achieving the highest scores in Text Editing and Character Preservation

We evaluate image-to-image models, including our FLUX.1 Kontext models across six KontextBench tasks. FLUX.1 Kontext [pro] consistently ranks among the top performers across all tasks, achieving the highest scores in text editing and character preservation (see Figure above) while consistently outperforming competing state-of-the-art models in inference speed (see Figure below)

FLUX.1 Kontext models consistently achieve lower latencies than competing state-of-the-art models for both text-to-image generation (left) and image-editing (right)

We evaluate FLUX.1 Kontext on text-to-image benchmarks across multiple quality dimensions. FLUX.1 Kontext models demonstrate competitive performance across aesthetics, prompt following, typography, and realism benchmarks.

left: input image;
middle: edit from input: “tilt her head towards the camera”,
right: “make her laugh”

left: input image;
middle: edit from input: “change the ‘YOU HAD ME AT BEER’ to ‘YOU HAD ME AT CONTEXT’”,
right: “change the setting to a night club”

Failure Cases:

FLUX.1 Kontext exhibits some limitations in its current implementation. Excessive multi-turn editing sessions can introduce visual artifacts that degrade image quality. The model occasionally fails to follow instructions accurately, ignoring specific prompt requirements in rare cases. World knowledge remains limited, affecting the model's ability to generate contextually accurate content. Additionally, the distillation process can introduce visual artifacts that impact output fidelity.

Illustration of a FLUX.1 Kontext failure case: After six iterative edits, the generation is visually degraded and contains visible artifacts.

A FLUX API Demo: Introducing The BFL Playground

Since launch, we have been consistently asked to make our models easier to test and demo. Today, we are introducing the FLUX Playground: A streamlined interface for testing our most advanced FLUX models without technical integration.

The Playground allows developers and teams to validate use cases, demonstrate capabilities to stakeholders, and experiment with advanced image generation in real-time. Whether evaluating technical feasibility or showcasing results to decision-makers, the Playground provides immediate access to assess FLUX's capabilities before moving to full API implementation.

At BFL, our mission is to build the most advanced models and infrastructure for media generation.The Playground serves as an entry point to the BFL API, designed to accelerate the path from evaluation to production deployment. It is available, today, at https://playground.bfl.ai.

We're just getting started.If you want to join us on our mission, we are actively hiring talented individuals across multiple roles. Apply here.

Black Forest Labs is excited to announce the launch of the FLUX Pro Finetuning API, bringing unprecedented customization capabilities to our flagship FLUX Pro model line.

Generative text-to-image models often do not fully capture a creator’s unique vision, and have insufficient knowledge about specific objects, brands or visual styles. With the FLUX Pro Finetuning API, creators can customize FLUX.1 [pro] with their own images and concepts to give them more control over the final results.

Examples of user-provided images with content that FLUX has no or limited knowledge of, such as specific persons, pets, clothing, stickers, and styles.

Trained on user-provided images, each FLUX Pro finetune is a user-customized FLUX Pro model. Each finetune maintains the generative versatility of the base model, but allows creators to easily reimagine user-provided content via text prompts. By enabling targeted finetuning of our highest quality models with as few as 1-5 example images, this new tool opens new horizons for customized content creation, and enables countless use cases including marketing, branding and storytelling.

Customized Content Creation at Unprecedented Quality

The FLUX Pro Finetuning represents the most powerful finetuning tool to date and sets a new industry standard for customized media creation with generative AI. In a user study we conducted, FLUX Pro finetuning results were preferred 68.9% of the time over other available finetuning services using FLUX.1 [dev].

Once a FLUX Pro finetune is created, it can be seamlessly applied across our entire model suite without any additional adaptation. This includes our most powerful models – FLUX.1 [pro] and FLUX1.1 [pro] and our complete FLUX Tools suite.

This versatility enables the creation of high-quality, customized content with resolutions up to 4 megapixels. Professional creatives and designers can now access AI tools that reliably preserve essential brand properties and style while maintaining character consistency across all generated content.

Combining finetuning with FLUX.1 Fill [pro] enables personalized inpainting for iterative editing of a given image.

Another possible application is combining finetuning with FLUX.1 Depth [pro] to unlock personalized content generation with structural control.

Customized FLUX finetunes can now be created via our newly available API Endpoint. Learn more about how to train your own finetune and optimally combine it with our most powerful models by following our Finetuning Guide.

Partnering with BurdaVerlag: Bringing FLUX and FLUX Pro Finetuning to Professional Creators

Our partnership with BurdaVerlag, a leading media and entertainment group based in Germany, showcases the potential of the FLUX and FLUX Pro Finetuning API in the hands of professional content creators.

The FLUX Finetuning API allows Burda’s creative teams to efficiently develop customized versions of FLUX tailored to each brand’s unique visual identity. Compelling and consistent visual narratives can then be created across the entirety of their diverse media portfolio, as shown for their cherished children’s brand Lissy PONY.

This integration fundamentally transforms Burda’s media creation workflow, enabling their creative teams to produce brand-consistent visuals at an unprecedented scale. With the help of FLUX finetuned models, Burda’s designers can create compelling images in minutes, all while maintaining the distinctive visual elements that define its brand’s identities. This not only accelerates content production for Burda, but also empowers its creators to explore new creative directions within established brand guidelines, leading to richer and more diverse content offerings across its digital and print platforms.

By bringing AI customization to leading media houses, we’re transforming visual content creation while preserving each brand’s distinct voice. For further reference, access the Finetuning API, Documentation, and our Finetuning API Guide.

Revolutionary Performance on NVIDIA RTX GPUs

Our new collaboration with NVIDIA marks a significant leap forward in making our FLUX models more universally accessible and efficient. Through reduced memory requirements, faster performance, support for greater GPU variety, and new capabilities for 3D environments, together we are widening the global community of creators, developers, and tinkerers.

Our FLUX models are now optimized to deliver exceptional performance on the newly announced GeForce RTX 50 Series GPUs. With the introduction of FP4 compute support on these GPUs, powered by the NVIDIA Blackwell architecture, we’re pushing the boundaries of what’s possible on RTX AI PCs.

Our flagship FLUX models showcase this breakthrough, achieving remarkable efficiency improvements: for example, FLUX.1 [dev] requires only 10GB of VRAM while delivering 2x faster performance on GeForce RTX 5090 compared with GeForce RTX 4090 using plain BF16. This breakthrough in memory optimization and speed means creators can now generate more high-quality images, faster, on their RTX AI PCs.

Images above are generated with FLUX.1 [dev] in FP4.

New Possibilities for 3D Creation

For users interested in integrating the FLUX NIM microservice into their workflows, we have collaborated with NVIDIA to launch the NVIDIA AI Blueprint for 3D-guided generative AI. This packaged workflow allows users to guide image generation by laying out a scene in 3D applications like Blender, and using that composition with the FLUX NIM microservice to generate images that adhere to the scene. This integration simplifies image generation control and showcases what’s possible with FLUX models.

Wider Availability and Access

We’re committed to making these innovations easily accessible to our community:

• Our optimized models will be available in FP4 format on Hugging Face in early February.
• The FLUX NIM will be available through ComfyUI and ai.nvidia.com in February.
• The NVIDIA AI Blueprint for 3D-guided generative AI will be accessible via GitHub with a convenient one-click installer in February.

This collaboration with NVIDIA underscores our commitment to democratizing access to cutting-edge AI technology while delivering unprecedented performance improvements. Stay tuned for more updates as we continue to push the boundaries of what’s possible in media creation.

Comparison between BF16 (left) and FP4 (right) for FLUX.1 [dev].

Today, we are adding new high-resolution capabilities to FLUX1.1 [pro], extending its functionality to support 4x higher image resolutions (up to 4MP) while maintaining an impressive generation time of only 10 seconds per sample.

Ultra Mode

FLUX1.1 [pro] – ultra mode: This option enables image generation at four times the resolution of standard FLUX1.1 [pro], without sacrificing prompt adherence. Unlike many high-resolution models that experience significant slowdowns at higher resolutions, our performance benchmarks show sustained fast generation times—over 2.5x faster than comparable high-resolution offerings. This model is available at a competitive price of $0.06 per image.

Raw Mode

FLUX1.1 [pro] – raw mode: For creators seeking authenticity, our new raw mode captures the genuine feel of candid photography. Toggle this feature to generate images with a less synthetic, more natural aesthetic. Compared to other text-to-image models, raw mode significantly increases diversity in human subjects and enhances the realism of nature photography.

Ready to experience the next generation of image creation? Access FLUX1.1 [pro] through our API today.