local version for OmniAICreator/Anime-Llasa-3B-Captions-Demo

[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset

A Deep Learning Approach for Password Guessing (https://arxiv.org/abs/1709.00440)

UniVid: The Open-Source Unified Video Model

Infinite-Forcing: Towards Infinite-Long Video Generation

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

High-Quality Text-to-Video Generation with Alpha Channel

Lynx: Towards High-Fidelity Personalized Video Generation

EasyLlasa は 5～15秒の日本語音声と日本語テキストから日本語音声を生成する TSTS (TextSpeechToSpeech) です。

to server only

Enable true multi gpu capability in Comfy UI using XDiT XFuser and FSDP

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

ComfyUI nodes for WanAnimate model input preprocessing

Cloud replacement for vacuum robots enabling local-only operation

Ace-Step Dataset Generator

MiMo-Audio: Audio Language Models are Few-Shot Learners

Cross-platform Plist Editor

RAM is all you need

Unofficial WIP LoRa Finetuning repository for VibeVoice

VibeVoice: Expressive, longform conversational speech synthesis. (Community fork)

Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.

Long-form streaming TTS system for multi-speaker dialogue generation

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning