{"id":672437,"date":"2025-05-30T03:28:39","date_gmt":"2025-05-30T00:28:39","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/black-forest-labs-kontext-ai-models-can-edit-pics-as-well-as-generate-them\/"},"modified":"2025-05-30T03:28:39","modified_gmt":"2025-05-30T00:28:39","slug":"black-forest-labs-kontext-ai-models-can-edit-pics-as-well-as-generate-them","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/black-forest-labs-kontext-ai-models-can-edit-pics-as-well-as-generate-them\/","title":{"rendered":"Black Forest Labs’ Kontext AI models can edit pics as well as generate them"},"content":{"rendered":"
\n

Black Forest Labs, the AI startup whose models once powered the image generation features of X\u2019s Grok chatbot, on Thursday released a new suite of image-generating models \u2014 some of which can both create and<\/em> edit pics. <\/p>\n

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<\/a>.<\/p>\n

\u201cThe Flux.1 Kontext models deliver state-of-the-art image generation results with strong prompt following, photorealistic rendering, and competitive typography \u2014 all at inference speeds up to 8x faster than current leading models,\u201d the company writes in its post.<\/p>\n

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\u2019s I\/O developer conference. Earlier this year, OpenAI brought a vastly improved image-generating model to ChatGPT \u2014 a model that quickly went viral for its ability to create art in the style of Studio Ghibli movies<\/a>.<\/p>\n

\n
\n
\n

Today we’re releasing FLUX.1 Kontext \u2013 a suite of generative flow matching models that allow you to generate and edit images.<\/p>\n

Unlike traditional text-to-image models, Kontext understands both text AND images as input, enabling true in-context generation and editing. pic.twitter.com\/zleJGuXDge<\/a><\/p>\n

\u2014 Black Forest Labs (@bfl_ml) May 29, 2025<\/a><\/p><\/blockquote>\n<\/div>\n<\/figure>\n

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 \u201cturns,\u201d all while preserving the characters and styles in the images. Flux.1 Kontex [max] focuses on speed, consistency, and adherence to prompts.<\/p>\n

\n
\n
\n

Hello FLUX.1 Kontext!<\/p>\n

Kontext is a new state-of-the-art image editing model from Black Forest Labs. It’s live now on Replicate.<\/p>\n

You can edit images with words: Change clothes, restyle scenes, rewrite text, all from a prompt. It just works \ud83d\udd25<\/p>\n

Pro and Max:\u2026 pic.twitter.com\/e5URxFewki<\/a><\/p>\n

\u2014 Replicate (@replicate) May 29, 2025<\/a><\/p><\/blockquote>\n<\/div>\n<\/figure>\n

Unlike some of Black Forest Labs\u2019 previous models, Flux.1 Kontex [pro] and Flux.1 Kontex [max] can\u2019t be download<\/a>ed for offline use. However, Black Forest Labs is making an \u201copen\u201d Kontext model, Flux.1 Kontext [dev], available in private beta for research and safety testing. <\/p>\n

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].<\/p>\n

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\u2019s Garry Tan.<\/p>\n

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.<\/p>\n<\/div>\n