Gpen-bfr-2048.pth -

The 2048 checkpoint is the result of the 1024‑pixel model on a progressively‑grown version of StyleGAN2 (weights duplicated to support 2048 output). No additional data beyond the synthetic pipeline was introduced; the model simply learns to extrapolate the StyleGAN2 latent space to higher spatial resolution.

| Dataset | Size | Content | |---------|------|---------| | (official StyleGAN2 pre‑training) | 70 k high‑quality portraits | Balanced gender/ethnicity, diverse ages, backgrounds. | | Synthetic Degradation Pipeline (used for BFR) | N/A (on‑the‑fly) | Randomly sampled combinations of: • Down‑sampling factors (2‑× to 16‑×) • Gaussian blur (σ = 0‑3) • Motion blur (kernel lengths up to 25 px) • JPEG compression (Q = 10‑100) • Additive Gaussian noise (σ = 0‑25) • Random color shift (γ, contrast). | | Real‑World BFR Test Set (e.g., CelebA‑HQ degraded, LFW‑BFR) | 5 k images | For evaluation only, not used in training. | gpen-bfr-2048.pth

gpen-bfr-2048.pth is a high-resolution pre-trained model weight for GPEN (GAN Prior Embedded Network) The 2048 checkpoint is the result of the

– Use VirusTotal or similar services before loading it with torch.load() – many malicious models have been distributed under plausible-sounding names. | | Synthetic Degradation Pipeline (used for BFR)

The "2048" indicates it is the highest-resolution version of the model, processing or generating faces at a

Community reviews suggest it often outperforms other popular restoration models like CodeFormer or GFPGAN in terms of sharpness and output quality. Availability and Deployment

# Generate an image image = model(noise)