Latest news with #BlackForestLabs
Yahoo
30-05-2025
- Business
- Yahoo
Black Forest Labs' Kontext AI models can edit pics as well as generate them
Black Forest Labs, the AI startup whose models once powered the image generation features of X's Grok chatbot, on Thursday released a new suite of image-generating models — some of which can both create and edit pics. The most capable of the models in the new family, called Flux.1 Kontext, can be prompted with text and, optionally, a reference image to create new images, writes Black Forest Labs in a blog post. "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," the company writes in its post. Flux.1 Kontext comes as the race to build competitive image generators heats up. Google debuted its latest image-generating model, Imagen 4, earlier this month at the company's I/O developer conference. Earlier this year, OpenAI brought a vastly improved image-generating model to ChatGPT — a model that quickly went viral for its ability to create art in the style of Studio Ghibli movies. There are two models in the Flux.1 Kontext family: Flux.1 Kontex [pro] and Flux.1 Kontex [max]. The former allows users to generate an image and refine it through multiple "turns," all while preserving the characters and styles in the images. Flux.1 Kontex [max] focuses on speed, consistency, and adherence to prompts. Unlike some of Black Forest Labs' previous models, Flux.1 Kontex [pro] and Flux.1 Kontex [max] can't be downloaded for offline use. However, Black Forest Labs is making an "open" Kontext model, Flux.1 Kontext [dev], available in private beta for research and safety testing. Black Forest Labs is also launching a model playground that allows users to try its models without having to sign up for a third-party service. New users get 200 credits, enough to generate around 12 images with Flux.1 Kontex [pro]. Black Forest Labs, based in Germany, was said to be in talks to raise $100 million at a $1 billion valuation toward the end of last year. Many of the founders hail from Stability AI, the creator of the notorious Stable Diffusion image-generating model. Backers include Andreessen Horowitz, Oculus co-founder Brendan Iribe, and Y Combinator's Garry Tan. In the months since it emerged from stealth, Black Forest Labs has released a number of new image-generating models and enterprise-focused services, including an API. This article originally appeared on TechCrunch at Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Business Wire
29-05-2025
- Business
- Business Wire
Black Forest Labs Launches FLUX.1 Kontext, a Breakthrough in Context-aware Image Generation and Editing
FREIBURG, Germany--(BUSINESS WIRE)--Black Forest Labs, Europe's fast-rising frontier AI research lab, announced today the release of FLUX.1 Kontext, a new suite of image generation models that introduce powerful in-context generating and editing capabilities. Kontext enables users to generate, retouch, and iteratively refine images from both text and visual inputs, without the need for finetuning or complex editing workflows. "FLUX.1 Kontext represents a fundamental shift from traditional editing approaches by unifying image generation and editing in a single flow matching architecture," said Robin Rombach, CEO and co-founder of Black Forest Labs. FLUX.1 Kontext is designed for creators, developers, and enterprises seeking precision and creative control. The model can understand and extract visual concepts from images, maintain stylistic and character consistency across multiple scenes, and apply localized edits with exceptional fidelity. This enables seamless visual storytelling, fast ideation, and highly targeted content generation, all at inference speeds up to 8x faster than leading alternatives. "FLUX.1 Kontext represents a fundamental shift from traditional editing approaches by unifying image generation and editing in a single flow matching architecture," said Robin Rombach, CEO and co-founder of Black Forest Labs. "Using simple flow matching training, we have achieved state-of-the-art character consistency across multi-turn edits while maintaining interactive inference speeds of 3-5 seconds at 1MP resolution. This enables truly iterative creative workflows that were previously impossible due to visual drift and latency constraints." A Complete Suite for In-Context Generation The FLUX.1 Kontext suite introduces two distinct models: Kontext [Pro] and Kontext [Max], each designed to meet the demands of advanced image generation and editing. Kontext [Pro] is built for iterative editing workflows. It generates images from text or reference images and supports local edits, scene transformations, and multi-step refinements while preserving character and stylistic consistency. Kontext [Max] offers maximum performance, combining exceptional prompt adherence, advanced typography handling, and premium rendering quality with no compromise on speed. Together, these models deliver photorealistic outputs with minimal latency and support a wide range of applications from rapid ideation to high-end creative production. A B2B Playground for Enterprise Evaluation As part of the rollout, Black Forest Labs is introducing the Playground, a browser-based demo environment designed for business users to explore the full capabilities of the FLUX.1 model suite. Tailored for enterprise evaluation, the Playground allows teams to validate internal use cases, demonstrate functionality to stakeholders, and experiment with advanced image generation in real time. Playground enables risk-free exploration and rapid demonstration of value, making it easy to assess the power of FLUX before committing to full integration. Additional components of the Kontext model suite will launch on a rolling basis over the coming weeks, including: Open-weights, distilled variant of Flux.1 Kontext Access of FLUX open-weights models for self-deployment with transparent pricing and instant commercial use rights. Kontext follows the success of FLUX.1 Dev, one of Hugging Face's most popular models with over 30 million downloads. To date, the FLUX.1 family of models have generated 700 million images via API. To learn more, visit About Black Forest Labs Black Forest Labs is a European frontier AI lab advancing the future of generative media. Founded by leading AI researchers, BFL develops state-of-the-art image and video generation systems that are performant, accessible, and responsibly deployed. With deep roots in foundational research, the company continuously builds advanced infrastructure to empower creators, developers, and forward-thinking enterprises to bring their imagination to life.
TechCrunch
29-05-2025
- Business
- TechCrunch
Black Forest Labs' Kontext AI models can edit pics as well as generate them
Black Forest Labs, the AI startup whose models once powered the image generation features of X's Grok chatbot, on Thursday released a new suite of image-generating models — some of which can both create and edit pics. The most capable of the models in the new family, called Flux.1 Kontext, can be prompted with text and, optionally, a reference image to create new images, writes Black Forest Labs in a blog post. '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,' the company writes in its post. Flux.1 Kontext comes as the race to build competitive image generators heats up. Google debuted its latest image-generating model, Imagen 4, earlier this month at the company's I/O developer conference. Earlier this year, OpenAI brought a vastly improved image-generating model to ChatGPT — a model that quickly went viral for its ability to create art in the style of Studio Ghibli movies. Today we're releasing FLUX.1 Kontext – a suite of generative flow matching models that allow you to generate and edit images. Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing. — Black Forest Labs (@bfl_ml) May 29, 2025 There's two models in the Flux.1 Kontext family: Flux.1 Kontex [pro] and Flux.1 Kontex [max]. The former allows users to generate an image and refine it through multiple 'turns,' all while preserving the characters and styles in the images. Flux.1 Kontex [max] focuses on speed, consistency, and adherence to prompts. Hello FLUX.1 Kontext! Kontext is a new state-of-the-art image editing model from Black Forest Labs. It's live now on Replicate. You can edit images with words: Change clothes, restyle scenes, rewrite text, all from a prompt. It just works 🔥 Pro and Max:… — Replicate (@replicate) May 29, 2025 Unlike some of Black Forest Labs' previous models, Flux.1 Kontex [pro] and Flux.1 Kontex [max] can't be downloaded for offline use. However, Black Forest Labs is making an 'open' Kontext model, Flux.1 Kontext [dev], available in private beta for research and safety testing. Black Forest Labs is also launching a model playground that allows users to try its models without having to sign up for a third-party service. New users get 200 credits, enough to generate around 12 images with Flux.1 Kontex [pro]. Techcrunch event Save now through June 4 for TechCrunch Sessions: AI Save $300 on your ticket to TC Sessions: AI—and get 50% off a second. Hear from leaders at OpenAI, Anthropic, Khosla Ventures, and more during a full day of expert insights, hands-on workshops, and high-impact networking. These low-rate deals disappear when the doors open on June 5. Exhibit at TechCrunch Sessions: AI Secure your spot at TC Sessions: AI and show 1,200+ decision-makers what you've built — without the big spend. Available through May 9 or while tables last. Berkeley, CA | REGISTER NOW Black Forest Labs, based in Germany, was said to be in talks to raise $100 million at a $1 billion valuation toward the end of last year. Many of the founders hail from Stability AI, the creator of the notorious Stable Diffusion image-generating model. Backers include Andreessen Horowitz, Oculus co-founder Brendan Iribe, and Y Combinator's Garry Tan. In the months since it emerged from stealth, Black Forest Labs has released a number of new image-generating models and enterprise-focused services including an API.
Techday NZ
07-05-2025
- Business
- Techday NZ
NVIDIA launches AI Blueprint for 3D image creation in Blender
NVIDIA has introduced a new AI Blueprint that enables users to generate images guided by 3D scenes using Blender. This tool combines basic 3D scene design with depth mapping to help control image composition more precisely during AI generation. At the core of the process is FLUX.1-dev, an AI model developed by Black Forest Labs, which interprets the scene's spatial layout alongside text prompts to produce visuals that match the intended design. Depth maps play a crucial role by providing the spatial context needed for the model to understand scene structure. This technique simplifies the process by removing the need for detailed textures or complex objects, instead relying on general spatial information. With the scenes rendered in 3D, users have the flexibility to move elements and adjust camera angles to suit their creative goals. The Blueprint includes an NVIDIA NIM microservice that helps deploy the FLUX.1-dev model efficiently on RTX GPUs, using TensorRT for faster inference. It's packaged with an installer and comprehensive deployment instructions, making it accessible for AI artists looking to integrate generative tools into their workflow. Beyond entry-level users, the Blueprint is also designed to accommodate advanced developers. It offers a customisable pipeline that can be modified for more sophisticated needs. NVIDIA provides supporting materials like sample assets, detailed documentation, and a preconfigured environment to help streamline experimentation and creation. Optimised for NVIDIA RTX AI PCs and workstations, the solution benefits from the company's Blackwell architecture. The FLUX.1-dev model has been fine-tuned using TensorRT and quantised to FP4 precision, resulting in more than double the inference speed compared to traditional FP16 PyTorch implementations. There are also FP8 model versions tailored for GPUs based on the Ada Lovelace architecture, further expanding compatibility and performance. Quantising to FP4 significantly reduces the model size, lowering memory requirements while maintaining high performance, cutting VRAM needs by more than half compared to FP16. Currently, NVIDIA offers ten NIM microservices across areas like image generation, natural language processing, speech AI, and computer vision. The company plans to continue building out its portfolio with more AI blueprints and services designed to accelerate creative and technical workflows.
Forbes
15-04-2025
- Business
- Forbes
30 Under 30 Europe Technology 2025: The Young Innovators Shaping The AI Revolution At Breakneck Speed
It's been little over a year since Freiburg, Germany-based Black Forest Labs launched in 2024, but it's made big waves in a short amount of time. Its AI is now the text-to-image generator integrated into the $6 billion (valuation) Mistral Al's Le Chat, and it raised over $31 million in a seed round led by Andreessen Horowitz in August. Led by 28-year olds Frederic Boesel and Jonas Muller—along with their over 30 cofounders—the company is positioning itself to be a big mover in AI, making the base models underpinning powerful image generation widely accessible. As Andreessen Horowitz wrote after investing, the Black Forest Labs team 'could accelerate innovation across a wide range of fields.' Sebastian Nevols for Forbes For nearly a decade, Forbes has highlighted young entrepreneurs for our annual 30 Under 30 Europe Technology list, with the help of nominations from the public. To be considered for this year's list, all candidates had to be under the age of 30 as of April 8, 2025, and never before named to an 30 Under 30 North America, Asia or Europe list. After months of reporting by Forbes editors, candidates were evaluated by a panel of judges including founder of London-based unicorn Faculty, Dr. Angie Ma; partner at Silicon Valley-based IVP, Eric Liaw; EQT Growth partner Carolina Brochado and Under 30 alum and Chainalysis cofounder Jonathan Levin. This year's cohort is full of founders who've made waves in AI just a year or two after founding. Caoimhe Murphy, 29 left another Forbes Under 30 alum, Synesthesia, in 2024 to cofound Anam, which creates AI avatars for customer service and sales. It's already attracting top tier clients like Spotify and German multinational Henkel. Sweden's Lovable, founded in 2023 by 24-year-old Fabian Hedin lets users spin up working apps with just some text prompts. And Georgina Steele, 29, founded U.K.-based Maiven last year, which developed AI that can flag potential breaches of environmental law. Others members of this year's list are making big impacts by disrupting older industries. Featured honoree Simon Hennes, the 27-year-old cofounder of Vivenu, says his ticketing platform is taking a tech-first, white label approach to event ticketing, giving organisers control over how they sell tickets and handle customer information. It's a different strategy to the major industry players like Ticketmaster, but Hennes thinks a fresh take on an old market is the way to shake things up. 'There are lots of Goliaths out there, right?' he told Forbes. 'There are big, big companies with massive funding, with thousands of people in seed with a big history, and decades of providing these services. It's not easy to compete with them, but at the same time, it doesn't change the fact that your mission is important and people buy into it.' Investors are confident that such bold approaches will pay off, and the companies on the Technology list have collectively raised more than $300 million in recent years. Among the companies who've scored big rounds, Vivenu has raised $60 million, Black Forest Labs $30 million and Lovable $20 million. Not that fundraising is everything. The mission comes first. Hennes says that his company doesn't yet need more funding as it's a profitable business. Still, he wants to double headcount and revenue growth over the next year. 'Our mission is to become the largest ticket provider globally, right? So we have a long term mission. It's not a short-term mission, it's not a mid-term mission. It's a long term mission.' The same will go for many of this year's Under 30 Europe group. They may have made big splashes in no time at all, but the road ahead will be long and, with some luck, prosperous. This year's list was edited by Thomas Brewster, Zoya Hasan and Iain Martin . For a link to our complete 30 Under 30 Europe Technology list, click here, and for full 30 Under 30 Europe coverage, click here.
