Black Forest Labs
Developers, product teams, agencies, and enterprises that need high-quality AI image and video generation for applications, services, or internal use.
Overview
Black Forest Labs is a frontier AI research lab focused on visual intelligence, developing the FLUX family of multimodal models for image, video, audio, and action-prediction. Founded by the original creators of Stable Diffusion, the company builds state-of-the-art technology for generating and understanding visual content. With a team of about 70 people, the lab operates from Freiburg, Germany, and San Francisco, and its models power millions of creations worldwide, from individual artists to enterprise applications. The company has raised over $450M in total funding, including a $300M Series B at a $3.25B post-money valuation, and is backed by leading investors.
What it does
Black Forest Labs develops the FLUX model family, which includes FLUX 3, FLUX.2, FLUX.2 Max, FLUX.2 Klein, and Flux Tools. These models generate images, videos, and audio from text, images, or keyframes, with capabilities such as native audio, up to 20-second video clips, and multilingual speech and effects. The models also support action-prediction for robotics, taking visual observations and text instructions to predict physical outcomes and robot control actions. The company offers access via API, open weights for self-hosting, and enterprise licensing.
Key features
- Multimodal generation: image, video, audio, and action-prediction in one model
- Text, image, or keyframe input for video generation
- Native audio generation with multilingual speech, effects, and ambience
- Up to 20-second video clips in a single generation
- Highly accurate text rendering and complex prompt handling for images
- Open weights available for self-hosting and customization
- API with pay-as-you-go pricing and no subscriptions
- Enterprise options with custom volume, SLA guarantees, and dedicated support
Use cases
- Generating images and videos for creative projects, marketing, and media
- Creating video content with optional audio for storytelling or presentations
- Building AI-powered applications that require visual generation
- Training AI models with synthetic data generated by FLUX models
- Robotics research and development using action-prediction capabilities
Pricing
Pay-as-you-go API pricing: $0.17/second for HD video, $0.29/second for FHD, $0.54/second for higher resolutions. Image generation starts at $0.014 per image for Klein 4B. Open weights licensing available with separate plans.
View current pricingPricing is gathered from the company's public pages and may change. Check the vendor's site before buying.
Pros and cons
Strengths
- State-of-the-art image generation quality, rivaling Midjourney
- Multimodal capabilities (image, video, audio) in a single model
- Flexible deployment options: API, open weights, or enterprise
- Pay-as-you-go pricing with no subscriptions or seat fees
- Strong backing with over $450M in funding and a $3.25B valuation
- Founded by original Stable Diffusion researchers, indicating deep expertise
Limitations
- Pricing is usage-based and can be costly for high-volume use (e.g., $0.17/second for HD video)
- No free tier; requires payment or contact sales for access
- Enterprise features and custom pricing require contacting sales
- Open weights licensing may have restrictions depending on the plan
What sets it apart
- Multimodal model covering image, video, audio, and action-prediction in one system
- Open weights availability for self-hosting and customization
- Founded by the original creators of Stable Diffusion, with a strong research pedigree
- Backed by significant funding and a high valuation, indicating market confidence
Frequently asked questions
What is FLUX 3?
FLUX 3 is the latest model from Black Forest Labs, a multimodal model that handles image, video, audio, and action-prediction in a single generation. It supports text, image, or keyframe inputs and can generate up to 20-second video clips with optional audio.
How does pricing work?
Pricing is pay-as-you-go with no subscriptions or seat fees. You pay only for what you generate. Video generation costs $0.17 per second for HD, $0.29 per second for FHD, and higher for other resolutions. Image generation starts at $0.014 per image for Klein 4B models.
Can I run FLUX models on my own infrastructure?
Yes, Black Forest Labs offers open weights for FLUX models, allowing you to deploy, customize, and fine-tune them on your own infrastructure. Licensing options are available for different use cases, including commercial and synthetic data generation.
What is the difference between the API and open weights?
The API provides easy integration and is built for production workloads at any scale, with pay-as-you-go pricing. Open weights give you full model access to deploy anywhere, with control over deployment, fine-tuning, and customization, but require a license.
Who is behind Black Forest Labs?
The founding team includes pioneers of Latent Diffusion, Stable Diffusion, and FLUX.1. They are known for creating Stable Diffusion, one of the most popular open-source image generation models.
Sources
This profile was compiled from the company's own pages and public web research.
Last researched August 16, 2026.
Manage this listing
Own this company? Update your listing information.