AuraFlow Models by fal
1 model2024
Last refreshed 2026-05-19. Next refresh: weekly.
Details
Researcherfal
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2024
Capabilities
MultimodalAll models
About
fal.ai's open-source flow-based text-to-image model family. AuraFlow was the largest open-source flow-matching image generation model at launch (6.8B parameters), achieving state-of-the-art results on GenEval using flow matching instead of traditional diffusion noise scheduling.
Decision facts
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
AuraFlowCurrent
Use when the workload needs image generation, 6.8B parameters, and multimodal inputs.
2024-07image generation6.8B parametersmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| AuraFlow | Use when the workload needs image generation, 6.8B parameters, and multimodal inputs. | 2024-07 | image generation6.8B parametersmultimodal inputs | Current |
Release Timeline
1 release group2024-07
1 current
AuraFlow
Currentimage generation6.8B parametersmultimodal inputs
Specifications(1 models)
| Model | Released | Parameters | Multimodal |
|---|---|---|---|
| AuraFlow | 2024-07 | 6.8B | Yes |