SUPIR este un sistem AI de upscaling și restaurare a imaginilor conceput pentru a elimina artefactele și a restaura calitatea fotografiilor din lumea reală. Funcționează ca un instrument de îmbunătățire și restaurare a imaginilor bazat pe difuzie, care utilizează scalarea modelelor la scară largă pentru a produce rezultate de înaltă rezoluție cu detalii fotorealiste.
Principalele funcționalități ale fanghua-yu/supir sunt: Image-Conditioned Generation, Image Restoration Models, Model Parameter Scaling, Diffusion-Based Upsamplers, AI Upscaling, Image Restoration, High-Fidelity Synthesis, Gradual Latent Upscaling.
Alternativele open-source pentru fanghua-yu/supir includ: spipm/depixelization_poc — This project is an AI upscaling framework and deep learning image restorer designed to estimate original source pixels… sczhou/codeformer — CodeFormer is a deep learning framework designed for the restoration and enhancement of facial images and video… vladmandic/sdnext — SD.Next is an all-in-one web interface and multi-backend inference engine for generating, editing, and processing… astriaai/headshots-starter — This project is an AI headshot generator and SaaS boilerplate designed to train custom models on uploaded photos to… xpixelgroup/diffbir — DiffBIR is a diffusion-based image restoration framework designed for blind image reconstruction. It utilizes… tntwise/real-video-enhancer — Real-Video-Enhancer is a cross-platform desktop application that utilizes neural networks to upscale resolution,…
This project is an AI upscaling framework and deep learning image restorer designed to estimate original source pixels from low-resolution inputs. It functions as a super-resolution reconstruction system that transforms pixelated images into high-resolution versions by restoring high-frequency details and sharpening edges. The system utilizes a convolutional neural network pipeline to analyze pixel data and perform digital image restoration. It employs pixel-shuffle upsampling to rearrange channel dimensions into spatial dimensions, which increases resolution while reducing checkerboard artif
CodeFormer is a deep learning framework designed for the restoration and enhancement of facial images and video sequences. It functions as a comprehensive processing engine capable of reconstructing high-quality facial features from degraded, blurry, or damaged inputs, while also providing tools for image upscaling and generative inpainting to fill missing or corrupted regions. The system distinguishes itself by utilizing a codebook-based quantization approach that maps input patches to high-quality facial representations, supported by transformer-based global modeling to ensure structural co
SD.Next is an all-in-one web interface and multi-backend inference engine for generating, editing, and processing images and videos using diffusion models. It functions as a comprehensive tool for diffusion model management and an automated image processing pipeline for bulk operations. The project is distinguished by its hardware-backend abstraction layer, which provides automatic detection and acceleration for NVIDIA CUDA, AMD ROCm, Intel OpenVINO, and DirectML. It features a headless generative API and a programmatic command interface, allowing users to trigger tasks via REST API or CLI wi
This project is an AI headshot generator and SaaS boilerplate designed to train custom models on uploaded photos to produce professional, high-resolution portraits. It functions as an image generation pipeline and model training orchestrator that manages the end-to-end workflow of processing user images to create stylized avatars. The system includes a credit-based monetization framework that handles payments via automated webhooks. It provides a complete infrastructure for AI-driven services, incorporating user account management and automated email notifications to alert users when their ge