[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
-
Updated
Nov 18, 2025 - Python
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
One-click Face Swapper and Restoration powered by insightface 🔥
ONNX-Powered Inference for State-of-the-Art Face Upscalers
Orchestrating AI for stunning lip-synced videos. Effortless workflow, exceptional results, all in one place.
当下热门的模糊人脸修复模型的部署,分别是:Codeformer,GFPGAN,GPEN,Restoreformer
Tensorrt implementation for ultra fast face restoration inside ComfyUI
Video restoration Processing Pipeline
GPU-accelerated face swapping API with 13 models, CodeFormer restoration, and VRAM-safe serial queue. Powered by insightface and FaceFusion.
RunPod Serverless Worker for GPU-accelerated face swapping with 13 models, CodeFormer restoration, and VRAM-safe serial queue. Powered by insightface and FaceFusion.
Generate a diverse dataset of 100 face-swapped images using the Inswapper model for training robust face-swap detection classifiers. 🖼️🔍
Codeformer Tensorrt Face Restoration
Ravana - open-source real-time face-swap SDK for images, video and webcam. HyperSwap/InSwapper, GFPGAN/GPEN, ONNX Runtime (CUDA, AMD DirectML, CPU).
Face Swap Magic - GPU-accelerated face-swap studio with a real-time visual editor — TensorRT inference, NVDEC/NVENC video I/O
Restaurador de diapositivas y fotos antiguas para Linux: revelado, escalado por GPU (Vulkan), reconstrucción de caras y banco de personas que avisa cuando la IA deja de parecerse al original.
Facial Police a perfect platform for the police authorities to identify the suspects or the criminals through CCTV footages. This provides a thorough facial reconstruction of the image and detection through their databases even from the bluriest image available through footage.
Python client for the CodeFormer API — blind face restoration for old photos and AI faces through a hosted endpoint
Free, local, batch photo-archive restorer: DeOldify colorization + CodeFormer face restoration for a whole folder of scans, with a review gallery, QA flags and Immich push.
Build a spike-driven state-space transformer for skeleton action recognition with topology-aware attention for NTU RGB+D and NW-UCLA
To associate your repository with the codeformer topic, visit your repo's landing page and select "manage topics."