Stars
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Industry leading face manipulation platform
Official implementations for paper: VACE: All-in-One Video Creation and Editing
FastVideo is a unified framework for accelerated video generation.
JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.
👤🔍 | BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation | In PyTorch >> ONNX Runtime Inference
Create masonry layouts based on your CSS grid values 🎉
Official Implementation of LatentSwap:An Efficient Latent Code Mapping Framework for Face Swapping
This project implements realistic face swapping methods, this approach ensures high realism, natural blending, and minimal artifacts
ReSwapper aims to reproduce the implementation of inswapper. This repository provides code for training, inference, and includes pretrained weights.
This repository gives the official implementation of Realistic and Efficient Face Swapping: A Unified Approach with Diffusion Models (WACV 2025)
InstantID-ROME: Improved Identity-Preserving Generation in Seconds 🔥
[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Based on EcomID, PuLID and InstantID. Swap face between two photos with high ID fidelity, include hair feature.
unofficial implementation of Few-Shot Head Swapping in the Wild
This is a HeadSwap project not only face
[ACM TOG, 2024] Identity-Preserving Face Swapping via Dual Surrogate Generative Models
DeepFace-Img2Img is a project designed solely for face swapping in images. By using a source image and a target image, it facilitates the swapping of faces between them.
Unofficial implementation of the paper: RobustSwap: A Simple yet Robust Face Swapping Model against Attribute Leakage
⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral)
Implementation of “DreamDiffusion: Generating High-Quality Images from Brain EEG Signals”
Lumina-T2X is a unified framework for Text to Any Modality Generation
Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Image captioning with a locally stored Large Language Model (LLM)
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥