AuraFlow
auraflow
Open SourceMultimodal
About
AuraFlow by fal.ai. At 6.8B parameters, the largest open-source flow-based text-to-image model at launch. Uses flow matching (direct noise-to-image mapping) rather than traditional diffusion, achieving strong semantic coherence for complex multi-object compositions. Released July 2024 under Apache 2.0. Available on HuggingFace (fal/AuraFlow) and Fal API (fal-ai/aura-flow).
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudioFine-tuning
