Gpen-bfr-2048.pth ❲PREMIUM ◎❳

: Weights can be found via ModelScope or Hugging Face .

| Attribute | Value | |-----------|-------| | | PyTorch checkpoint ( torch.save ) | | Size on disk | ≈ 2.1 GB (fp32) – ~1.1 GB when saved with torch.save(..., _use_new_zipfile_serialization=False, pickle_protocol=4) and torch.save(..., dtype=torch.float16) | | Top‑level keys | 'encoder', 'mapper', 'generator', 'args' | | encoder | state_dict of a ResNet‑50 (BN layers stripped) | | mapper | 2‑layer MLP (512 → 512) plus LayerNorm | | generator | StyleGAN2 weights (including the new 2048‑pixel synthesis blocks) | | args | Namespace containing training hyper‑parameters, input resolution, output resolution, and a version string ( GPEN-BFR-v2.0-2048 ). | | Compatibility | Requires PyTorch ≥ 1.8 and CUDA ≥ 11.0 (or CPU‑only fallback). The checkpoint can be loaded on any device with the same architecture (ResNet‑50 + StyleGAN2). | gpen-bfr-2048.pth

: Often used alongside colorization models to make black-and-white portraits look modern. Inpainting : Repairing damaged parts of a face in an image. 🚀 How it Works : Weights can be found via ModelScope or Hugging Face

Can help "fill in" parts of a face that are missing due to physical damage to a photo. Where is it used? You’ll typically find this file being called for in: The checkpoint can be loaded on any device

If you encountered this filename in a project, tutorial, or repository:

: Restores low-quality, blurry, or noisy facial images.