FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes

A Large-scale Video Action Dataset

make the video have shot change, for t2v and i2v

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

In our implementation of Qwen-Image-Edit, we employ block causal attention to improve inference speed.

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation.

[Tech Report] Alive: A Unified Audio-Video Generation Model

Official implementation of "Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound". IEEE TASLP 2025.

Nodes for high resolution outputs and high frame numbers using LTX-2 in ComfyUI

Code for 'JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion'

All available LTX-2 models, encoders, workflows, LoRAs for ComfyUI

Official code for StoryMem: Multi-shot Long Video Storytelling with Memory

ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.

MotionAgent is your AI assistent to convert ideas into motion pictures.

MS-Agent: a lightweight framework to empower agentic execution of complex tasks

AgentEvolver: Towards Efficient Self-Evolving Agent System

Fully automatic censorship removal for language models

Cache-DiT Node for Comfyui

A Simple Implementation of Qwen3-TTS's ComfyUI

ComfyUI Custom Node for HeartMuLa AI Music Generation and Transcript Text

A curated list of research and projects on world models

a set of utils for comfyui edit model

this can help make prompts for simple camera and weather lighting and such

SD.Next Quantization Engine

Load and run SDNQ quantized models in ComfyUI with 50-75% VRAM savings!

A simple custom node for ComfyUI that allows Qwen-Image to perform prompt expansion using the already-loaded text-encoder.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

ComfyUI custom nodes for LTXV audio-video separation sampling and latent preparation. PainterSamplerLTXV: Advanced sampler with external sigmas support - PainterLTXVtoVideo: LTXV latent preparation…