How it works Flux Depth Dev?
Flux Depth Dev is an open-weights model by Black Forest Labs that relies on the depth map of the source frame: you describe the desired changes, while the perspective, volumes, and relative positioning of objects remain the same. This is not random generation, but controlled editing where the scene structure must match the reference. Through BotHub, the model works without a VPN or foreign card; pay with a Russian card in rubles and only for actual usage. Over 250 other models are available in one window, making it easy to compare results with other image generators, and switching is done without rewriting the integration—access is via a unified OpenAI-compatible API, with data transmitted using AES-GCM encryption. For companies, BotHub provides contracts, invoices, and electronic document management, along with an admin panel with employee limits. Simple scenarios: change interior finishes and furniture while keeping the layout; place a product in a new environment without moving it in the frame; create a series of variations for a storyboard; carefully rework an architectural render; maintain consistent geometry in a series of illustrations.Frequently asked questions about Flux Depth 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-depth-dev creates images from text descriptions and can rely on an uploaded reference, preserving the depth and geometry of the scene. It is suitable when you need to recolor or redraw an interior, object, or frame while keeping the composition and proportions the same.
You get a finished raster image as output, which can be downloaded or passed on via API. The specific resolution and format depend on the request parameters; they are not fixed in our data, so rely on the results of your first generations.
Reasoning before answering is not noted in our data: it is an image generator, it outputs a picture, not a chain of thought. If you need to think through the scene in words, assemble the prompt in a BotHub text model and switch back immediately in the same window.
Function calling and strict JSON are not noted in our data for this model — its task is to output an image. For orchestration, connect flux-depth-dev via the unified BotHub OpenAI-compatible API, and assemble structured responses using a text model in the same integration.
You can upload images — that is exactly what the model is designed for: it reads the depth from the reference and builds a new frame with the same structure. Audio and video input are not noted in our data, so count on text and images.
Nothing is recorded in our data regarding the prompt language, so we will not promise the accuracy of formulations — check it with your own scenario. BotHub itself is Russian-speaking: interface, support, and payment in rubles, access without VPN or foreign cards.