Official repository for LTX-Video

LTX-Video Support for ComfyUI

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画

[AAAI 2025] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"

[NeurIPS D&B Track 2024] Official implementation of HumanVid

[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation

ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation [TMLR 2024]

[CVPR'25 Highlight] Official implementation for paper - LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

[ICCV 2025] AnyI2V: Animating Any Conditional Image with Motion Control Generation

[WACV 2020] ImaGINator: Conditional Spatio-Temporal GAN for Video Generation

Official implementation of: "TextOCVP: Object-Centric Video Prediction with Language Guidance" by Villar-Corrales, Plepi & Behnke. TMLR. 2026

🎶 Enhance audio quality with ComfyUI-AudioSR, a versatile tool for upscaling sounds to 48kHz for better clarity and listening experience.

🎤 Generate and customize voices with ComfyUI HAIGC Qwen3TTS, integrating powerful voice synthesis and cloning capabilities for diverse applications.

Wan 2.2 Image-to-Video inference pipeline deployed on RunPod Serverless using a Docker-based GPU setup.

Generate, analyze, and refine AceStep 1.5 SFT music in ComfyUI with stronger control, LoRA stacking, and quality-focused nodes

Apply realistic sensor noise, analog artifacts, and camera metadata to AI-generated images using this custom ComfyUI node suite for research and photorealism.

🚀 Control model allocation on any device, reduce OOM errors, and enhance multi-GPU workflows with seamless memory management.

A script to video generator which processes the input script and generates video, by using Hugging Face models, RIFE and FFmpeg, deployed using Django(dev) server.