ffhqdat-4x-upscaler
supersambat
4x face image upscaler trained on FFHQ dataset using DAT (Dual Aggregation Transformer) architecture. Optimized for portrait and face photos.
- Context window
- — tokens
- Input cost
- —
- Output cost
- —
- Latency (p50)
- —
Compare Models
Run side-by-side checks for pricing, context window, and latency.