How it works FLUX Kontext Dev?
FLUX Kontext Dev is an open-weights version of FLUX.1 Kontext by Black Forest Labs. The model works within the context of an initial image: you can use it not only to create a frame from a text description but also to rework an existing one—replace an object, adjust the background, or change the style while preserving the composition and character recognition. Unlike other Kontext variants, this one features open-weights publication. In BotHub, it is accessible from Russia without a VPN or foreign card; you pay with a Russian card in rubles, only for what you use (caps), with no subscription. With over 250 models in one window, you can easily run the same reference through multiple generators to choose the best frame. For production tasks, there is a unified OpenAI-compatible API and corporate access via contract with invoicing and electronic document management. It is useful when you need dozens of variations for a product card or banner, editing photos for social media, creating concepts and storyboards, illustrating articles, or integrating image editing into your own service.Frequently asked questions about FLUX Kontext Dev
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
flux-kontext-dev creates images from text descriptions and reworks existing images based on a reference. It is suitable for concepts, illustrations, banners, variations of a single scene, and precise edits: replacing details, changing backgrounds or styles, and assembling a series of frames with a consistent visual style.
The model provides a finished image that can be downloaded or sent directly to the next iteration. Specific resolution and aspect ratio depend on the request and generation settings. The prompt length is limited to a 4095-token context, so a detailed scene description will fit.
According to our data, a separate reasoning mode for flux-kontext-dev is not specified: it is a generative image model that immediately turns a description or reference into an image. You define the scene logic in the prompt, and it is convenient to achieve the desired result through short iterations and edits.
According to our data, function calling and strict JSON output are not supported by this model—its task is to provide an image. However, you can access flux-kontext-dev via the unified OpenAI-compatible BotHub API: you describe the scenario in your code and connect the model as a pipeline step.
Images—yes: the image-to-image mode accepts a picture and modifies it according to your description, preserving the composition or, conversely, reimagining it. Audio and video input are not supported according to our data; for such formats, choose specialized models in the same BotHub window.
We do not have data on which prompt languages the model works with, so we cannot make any promises—test it on your task in a couple of iterations. BotHub itself is Russian-speaking: the interface and support are in Russian, payment is via Russian cards, and access is available without a VPN or foreign card.