AIFSH
Follow
Stars
DeepFaceLab is the leading software for creating deepfakes.
Implementation of "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"
Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.
Implementation of “DreamDiffusion: Generating High-Quality Images from Brain EEG Signals”
Official code for VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
[CVPR 2024] Official PyTorch implementation of FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
[AAAI 2025] StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization
Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & outpaint areas.
[ICLR 2025] 3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation
The official implementation of ”RepVideo: Rethinking Cross-Layer Representation for Video Generation“
[ArXiv 2024] X-Dyna: Expressive Dynamic Human Image Animation
Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis
Motion-Controllable Video Diffusion via Warped Noise
Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"
Official implementation of "MangaNinja: Line Art Colorization with Precise Reference Following"
Official implementation of paper: "SwinTExCo: Exemplar-based Video Colorization using Swin Transformer"
A feature-rich command-line audio/video downloader
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution
[WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.
NVIDIA AI Blueprint for digital human for customer service.
Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
Offical implementation of "SM3Det: A Unified Model for Multi-Modal Remote Sensing Object Detection"
[NeurIPS 2024] SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models