Features
Unified multimodal understanding and generation in one model
Autoregressive framework with unified Transformer architecture
Decoupled visual encoding pathways (SigLIP-L + MLP adapters)
Text-to-image generation with instruction following
Image understanding (description, analysis)
Available in 1B and 7B parameter variants
MIT license, open-source on Hugging Face and GitHub
WebGPU support for in-browser inference (1B model)
Compatible with ComfyUI via community nodes
Bidirectional image-text interaction
Optimized training with extended datasets and stability techniques
Model sizes: 1.3B (Janus), 1.3B (JanusFlow), 1B, 7B checkpoints
Sequence length 4096 for all models
Integration with Hugging Face and GitHub for deployment
Supports unrestricted commercial use
160+ beauty marker facial analysis
Personalized non-surgical glow-up protocol
Visual projection of best-looking self
Research-backed recommendations with citations
Tailored to ethnic background and demographics
Considers lifestyle factors (diet, stress, sleep)
Adjusts for natural aging patterns
Facial dimorphism analysis
Detailed ear shape and projection analysis
Refined eye scleral and limbal ring measurements
Sharper jaw geometry angle and inclination analysis
Lip texture and health analysis
Refined eyebrow analysis with Westmore boundaries
Face shape analysis section
