FLUX 3
FLUX 3 is a multimodal foundation model that jointly learns from images, video, and audio within one unified architecture, building a representation of how objects hold together, how things move, and how events sound. Built on the Self-Flow approach, it aligns multimodal generation and understanding in the same backbone so each modality constrains the others, sound matches impact, motion follows physical properties, and future events follow from the past. FLUX 3 can mix modalities and jointly generate images, video, and native audio from text prompts or references such as images, video, and audio. Its video capabilities include text-to-video, image-to-video animation, video-to-video transformation, generative video-and-audio continuation, keyframe-controlled transitions, multilingual dialogue, animated typography, diverse styles and aspect ratios, and agentic chaining into longer multi-shot sequences.
Learn more
Flux
Build hardware more efficiently with real-time collaboration, an easy-to-use simulator, and forkable community content. Leverage collective intelligence through modern sharing, permissions, and an easy-to-use version control system. We believe in the power of open-source. Get started quickly with an ever-expanding library of parts and schematics created by the Flux community. Finally, a programmable simulator that doesn’t require a PHD to use. Check your schematic before you build, all from the browser. Whether you're building a simple circuit board or designing hardware for the next Mars mission, Flux is where great hardware projects are born. Flux is a browser-based end-to-end electronic design tool that breaks down barriers. Flux is making something new, and we’re doing in a new way. It’s called building in the open. Join our community of engineers, makers, and entrepreneurs who are passionate about improving hardware design tools.
Learn more
FLUX.2 [max]
FLUX.2 [max] is the flagship image-generation and editing model in the FLUX.2 family from Black Forest Labs that delivers top-tier photorealistic output with professional-grade quality and unmatched consistency across styles, objects, characters, and scenes. It supports grounded generation that can incorporate real-time contextual information, enabling visuals that reflect current trends, environments, and detailed prompt intent while maintaining coherence and structure. It excels at producing marketplace-ready product photos, cinematic visuals, logo and brand assets, and high-fidelity creative imagery with precise control over colors, lighting, composition, and textures, and it preserves identity even through complex edits and multi-reference inputs. FLUX.2 [max] handles detailed features such as character proportions, facial expressions, typography, and spatial reasoning with high stability, making it suitable for iterative creative workflows.
Learn more
Martini
Join the growing community of integration ninjas using Martini™ to integrate faster. Gloop eliminates the grunt work required when creating services for application and data integration, building APIs, and managing data. Gloop makes it easy to perform common development tasks such as mapping and transforming data, iterating over arrays, executing if-else and switch-case logic, invoking external code, running jobs in parallel, and so much more. Flux is Martini’s event based workflow engine for managing asynchronous workflows and event based triggers of Gloop microservices. With Flux you can invoke Gloop microservices sequentially, passing the output of one to the other, and/or in parallel, and Flux will maintain the state of each execution for you. Flux workflows are created visually by dragging Flux states onto a canvas and selecting the Gloop microservice you would like executed when the state is invoked.
Learn more