Building visual intelligence with multimodal AI models
Faster frame generation with higher image quality than NVIDIA DLSS Frame Generation
Stage
Startup
MVP
Founded
2024
Not given
Based in
DE
Not given
Pricing model
Freemium
Open source
Pricing
Pay-as-you-go API pricing: FLUX 3 Image at $0.048 per image, FLUX.1 [dev] at $0.025 per image, FLUX.1 [pro] at $0.04 per image, FLUX 1.1 [pro] Ultra at $0.06 per image, FLUX.1 Kontext [max] at $0.08 per image, FLUX Deblur from $0.004 per megapixel, FLUX.1 Fill [pro] at $0.05 per image, FLUX VTO at $
Not given
Key features
FLUX 3 multimodal model for image, video, audio and action prediction
Text to image generation with accurate text rendering
Video generation up to 20 seconds with optional audio
Multilingual speech and audio generation
Robotics action prediction for visual observations and control
Pay-as-you-go API pricing
Open weights models for self-hosted deployment
Browser-based playground for experimentation
Enterprise licensing with SOC 2 and ISO 27001 compliance
Fine-tuning and LoRA customization rights
1.01ms per frame generation on NVIDIA RTX 5090 at 4K 2X
214MB GPU memory at 4K
Super resolution support
Ray reconstruction capabilities
Native Metal support on Apple silicon
What makes it different
Single unified model handling multiple modalities: images, video, audio, and robotics
Founded by pioneers of foundational diffusion AI research
Flexible deployment: API, open weights, or playground
Enterprise-grade infrastructure with volume discounts and SLA guarantees
Powers millions of creations from individual artists to enterprise applications
Higher image quality than NVIDIA DLSS Frame Generation
Uses 62% less GPU memory than DLSS Frame Generation