← Back to all generators

tencentarc/vqfr

Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

Capabilities

Reference Images

Cost

Community model (estimated from hardware time)

Input Parameters

image required string

Input image. Output restored faces and whole image.

aligned boolean

Input are aligned faces.

Default: false
Version: f9085ea5bf9c Updated: 2/26/2026 601.9K runs