![FLUX.2 [pro]](data:image/svg+xml;base64,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)
FLUX.2 [pro]
Version: 1
Direct from Azure models
Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:- Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
- Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all as part of one Microsoft Foundry platform.
- Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
- Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.
Key capabilities
- Text to image
- Image to image
- High fidelity editing
About this model
Generate and edit images through both text and image prompts. FLUX.2-pro raises the bar with 4MP photorealistic quality, multi‑reference identity stability, and brand‑accurate color & text, enabling predictable, high‑fidelity creative at scale.Key model capabilities
The model provides powerful text-to-image and image-editing capabilities: Production‑grade quality up to 4MP: High‑fidelity, coherent scenes with realistic lighting, spatial logic, and fine detail that close the gap with photography. Multi‑reference consistency: Lock character or product identity across an entire campaign (multiple references), so assets stay visually consistent from shot to shot. Brand‑accurate results: Exact hex‑color matching, reliable typography, and structured controls (JSON, pose guidance) mean fewer manual fixes and stronger brand compliance. Strong prompt fidelity for complex directions: Precise positioning, physics‑aware lighting, and composition control plus 32K token support for long, detailed workflows. Balanced speed and quality: Designed to deliver maximum quality while keeping generation times practical (often under 10s), enabling real‑world production pipelines.Use cases
See Responsible AI for additional considerations for responsible use.Key use cases
The model is intended for broad commercial and research use. The model provides powerful text-to-image and image-editing capabilities:- Change existing images based on an edit instruction.
- Have character, style and object reference without any finetuning.
- Robust consistency allows users to refine an image through multiple successive edits with minimal visual drift.
Out of scope use cases
The provider has not supplied this information.Pricing
Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.Technical specs
The provider has not supplied this information.Training cut-off date
The provider has not supplied this information.Training time
The provider has not supplied this information.Input formats
The provider has not supplied this information.Output formats
- JPEG, PNG
Supported languages
EnglishSample JSON response
The provider has not supplied this information.Model architecture
Flux.2-pro is a multimodal flow matching model.Long context
The provider has not supplied this information.Optimizing model performance
The provider has not supplied this information.Additional assets
Training disclosure
Training, testing and validation
We filtered pre-training data for multiple categories of "not safe for work" (NSFW) content to help prevent a user generating unlawful content in response to text prompts or uploaded images. We have partnered with the Internet Watch Foundation, an independent nonprofit organization dedicated to preventing online abuse, to filter known child sexual abuse material (CSAM) from post-training data. Subsequently, we undertook multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse.Distribution
Distribution channels
The provider has not supplied this information.More information
Model developer: Black Forest Labs Model Release Date: November 25, 2025 Black Forest Labs is committed to the responsible development of generative AI technology. Prior to releasing FLUX.2-pro, we evaluated and mitigated a number of risks in our models and services, including the generation of unlawful content. We implemented a series of pre-release mitigations to help prevent misuse by third parties, with additional post-release mitigations to help address residual risks:- Pre-training mitigation. We filtered pre-training data for multiple categories of "not safe for work" (NSFW) content to help prevent a user generating unlawful content in response to text prompts or uploaded images.
- Post-training mitigation. We have partnered with the Internet Watch Foundation, an independent nonprofit organization dedicated to preventing online abuse, to filter known child sexual abuse material (CSAM) from post-training data. Subsequently, we undertook multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse. By inhibiting certain behaviors and concepts in the trained model, these techniques can help to prevent a user generating synthetic CSAM or nonconsensual intimate imagery (NCII) from a text prompt, or transforming an uploaded image into synthetic CSAM or NCII.
Responsible AI considerations
Black Forest Lab’s FLUX.2-pro poses an elevated risk of producing content protected by copyright and other intellectual property rights. When deployed via Microsoft Foundry, prompts and completions are passed through a default configuration of classification models to detect and prevent the output of harmful content. However, these models do not address the above types of content. As with any model, customers should conduct thorough evaluations on production systems before launching, as well as appropriate post-launch monitoring. All customers must comply with the Acceptable Use Policy and Microsoft Enterprise AI Services Code of Conduct. Configuration options for content filtering vary when you deploy a model for production in Azure AI Black Forest Lab’s FLUX.2-pro is configured to block nudity and other sexual content. This restriction is mandatory and non-configurableSafety techniques
Black Forest Labs is committed to the responsible development of generative AI technology. Prior to releasing FLUX.2-pro, we evaluated and mitigated a number of risks in our models and services, including the generation of unlawful content. We implemented a series of pre-release mitigations to help prevent misuse by third parties, with additional post-release mitigations to help address residual risks:- Pre-training mitigation. We filtered pre-training data for multiple categories of "not safe for work" (NSFW) content to help prevent a user generating unlawful content in response to text prompts or uploaded images.
- Post-training mitigation. We have partnered with the Internet Watch Foundation, an independent nonprofit organization dedicated to preventing online abuse, to filter known child sexual abuse material (CSAM) from post-training data. Subsequently, we undertook multiple rounds of targeted fine-tuning to provide additional mitigation against potential abuse. By inhibiting certain behaviors and concepts in the trained model, these techniques can help to prevent a user generating synthetic CSAM or nonconsensual intimate imagery (NCII) from a text prompt, or transforming an uploaded image into synthetic CSAM or NCII.
Known limitations
Acceptable use
Acceptable use policy
The provider has not supplied this information.Model Specifications
Context Length131072
LicenseCustom
Last UpdatedDecember 2025
Input TypeText,Image
Output TypeImage
ProviderBlack Forest Labs
Languages1 Language