Arbitrary-steps Image Super-resolution via Diffusion Inversion

[ICLR 22, TPAMI 24] Latent Image Animator

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

TorchCFM: a Conditional Flow Matching library

Memory-Guided Diffusion for Expressive Talking Video Generation

哔哩哔哩解析工具，一个辅助缓存下载B站视频番剧的APP，帮助你快速便捷的缓存B站视频和番剧。

从零手搓Flow Matching（Rectified Flow）

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

HunyuanVideo: A Systematic Framework For Large Video Generation Model

m3u8 视频在线提取工具

A feature-rich command-line audio/video downloader

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

[NeurIPS 2024] RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

Redux StyleModelApply adds more controls

Official repository of In-Context LoRA for Diffusion Transformers

PyTorch code for our ICCV 2023 paper "Dual Aggregation Transformer for Image Super-Resolution"

Official code for "Controllable Talking Face Generation by Implicit Facial Keypoints Editing"

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

[CVPR 2024 - Oral] Matching 2D Images in 3D: Metric Relative Pose from Metric Correspondences

ML models and internal tensors 3D visualizer

Excalidraw app for mac. Powered by pure SwiftUI.

Official implementation of "FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on"

EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation

ComfyUI nodes to edit videos using Genmo Mochi

Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers

Code for the paper Hybrid Spectrogram and Waveform Source Separation