FLUX 2 Dev
Neural Network
FLUX 2 Dev is a Black Forest Labs model for generating and editing images, including using references.
Specifications
- Input
- text, images
- Output
- images
- Aspect ratio
- custom, 1:1, 16:9, 3:2, 2:3, 4:5, 5:4, 9:16, 3:4, 4:3
- File formats
- WEBP, JPG, PNG
How it works FLUX 2 Dev?
FLUX 2 Dev is a Black Forest Labs model that creates images from text descriptions and edits existing pictures. Reference support helps set the style, composition, or character appearance and maintain consistency across a series of frames. Edits are made iteratively: describe what needs changing to get a new version. In BotHub, the model is accessible from Russia without a VPN or foreign card; payment is made with Russian cards in rubles based on actual usage, without a subscription. With over 250 models in one window, you can easily run the same prompt through multiple generators to choose the best frame. A unified OpenAI-compatible API connects generation to your product; requests are encrypted, and companies get contracts, invoices, and an admin panel with limits. For designers, it means visuals for social media, banners, and newsletters in a unified style; for marketers, product shots and campaign covers; for illustrators, concept art and storyboards based on references; and for product teams, precise replacement of details, backgrounds, and text on finished images.Frequently asked questions about FLUX 2 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-2-dev generates images from text descriptions and can process uploaded frames in image-to-image mode. It is suitable for concepts, illustrations, backgrounds, product cards, and variations based on references. In BotHub, the model is available from Russia without a VPN or foreign card, with payment in rubles.
The output is a raster image; specific resolutions and aspect ratios are not fixed in our data, so refer to the parameters available in the interface. The result largely depends on prompt detail: up to 4095 context tokens are allocated for the description, which is enough for a detailed scene, lighting, and style.
Our data does not indicate reasoning capabilities before answering, which is logical: flux-2-dev solves visual tasks, not text-based ones. You will not see chains of thought; the result is determined by the prompt and reference. If you need logic analysis, switch to a text model in the same BotHub window.
Function calling and structured JSON output are not noted in our data: the result is an image, not a text structure. You trigger the generation itself via the unified OpenAI-compatible BotHub API, so you can integrate flux-2-dev into a pipeline and replace the model later without rewriting the integration.
Images — yes: the model accepts an image as input and works in image-to-image mode, so you can set a reference for composition, style, or color and get a variation. Audio and video are not listed among the input formats in our data; there are separate models for them in BotHub.
We do not track the language of prompts and output in the model data, so we cannot make any promises — test it with your task. A practical tip: describe the scene with short, specific phrases and refine the prompt based on the results. The BotHub interface is in Russian, and payment is in rubles.