基于LTX2.3的向高清修复、视频去水印等编辑任务，提出统一的时空扩散技术路线：在 LTX-2.3 框架下以任务感知型适配器（Task-Aware Adapters）替代单一 LoRA 增量，通过轻量 Control-Transformer、零初始化残差连接与分层解耦注入机制，分别建模结构修复与纹理风格控制。为提升时序稳定性，方法在潜空间引入流引导注意力（Flow-Guided Latent Attention），结合跨帧滑窗关联与光流运动先验，降低闪烁并增强遮挡区域补全的一致性。针对三类核心场景，系统进一步整合语义遮挡重构、布局保持的指令编辑与频率域纹理精修，并采用渐进式多任务课程学习与任务路由策略，实现单模型多任务协同优化。
☆142Jun 1, 2026Updated 2 months ago
Alternatives and similar repositories for LTX2-ICEdit-Insight
Users that are interested in LTX2-ICEdit-Insight are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ComfyUI node to assist with Bernini video editing prompting (Ollama + Prompt Presets)☆137Jun 12, 2026Updated 2 months ago
- Comfy EverAnimate WIP☆17Jun 5, 2026Updated 2 months ago
- Pushing the Frontier of Long Video Generation Standalone, inference-only release for minute-level multi-shot audio-video generation with…☆56Jun 23, 2026Updated last month
- SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation☆39Mar 31, 2026Updated 4 months ago
- ☆474May 20, 2026Updated 2 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Standalone ComfyUI plugin for Wan 2.2 Bernini video generation and editing.☆135Jul 17, 2026Updated 3 weeks ago
- ComfyUI custom nodes for LongCat-AudioDiT \ Diffusion-based Zero-Shot Text-to-Speech☆134Apr 4, 2026Updated 4 months ago
- Fun-CineForge: A Unified Dataset Pipeline and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes☆21Apr 2, 2026Updated 4 months ago
- 一个基于利萨茹曲线的ComfyUI自定义节点,用于模拟平滑的手持相机抖动。A ComfyUI custom node for smooth handheld camera shake simulation based on Lissajous curves.☆49Feb 28, 2026Updated 5 months ago
- ComfyUI custom nodes for Fish Audio S2-Pro TTS — voice clone, multi-speaker, and text-to-speech☆279Apr 27, 2026Updated 3 months ago
- This is a ComfyUI plug-in for https://github.com/Netflix/void-model☆18Apr 20, 2026Updated 3 months ago
- MatAnyone in ComfyUI☆101Mar 15, 2026Updated 5 months ago
- ComfyUI nodes for SCAIL-Pose preprocessing☆322Apr 15, 2026Updated 4 months ago
- This is a ComfyUI plug-in for https://github.com/KlingTeam/UniVideo☆37Jan 19, 2026Updated 6 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Mel-Band RoFormer for Music Source Separation☆246Jan 30, 2026Updated 6 months ago
- LTX Director and a variety of other custom ComfyUI nodes and workflows☆1,951Jul 30, 2026Updated 2 weeks ago
- A universal swap node that supports ComfyUI native workflow, allowing 4_6G users to experience Klein9B or other large models☆116Updated this week
- Seamless video connection and multi-reference image support for Wan Animate and Scail-2☆399Jul 28, 2026Updated 2 weeks ago
- ☆563Mar 18, 2026Updated 4 months ago
- ComfyUI SAM3 node based on transformers / 基于 transformers 框架的 SAM3分割节点☆22Jan 29, 2026Updated 6 months ago
- A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captionin…☆153Aug 28, 2025Updated 11 months ago
- A ComfyUI custom node designed for LTX 2.3 MSR (Multiple-Subject-Reference) LoRA workflows.☆376Jul 14, 2026Updated last month
- ComfyUI-AudioLoopHelper☆16Jul 5, 2026Updated last month
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆158Jun 27, 2026Updated last month
- ☆30May 27, 2026Updated 2 months ago
- Text-to-audio and video-to-audio using Sony AI's Woosh foundation model.☆129May 7, 2026Updated 3 months ago
- An advanced Foveated Latent Sampler (FLS) for ComfyUI. Selective high-frequency local contrast boosting and stochastic texture noise inje…☆84May 21, 2026Updated 2 months ago
- ComfyUI nodes for WanAnimate model input preprocessing☆544May 27, 2026Updated 2 months ago
- Vibe coded nodes for LTX2.3☆246Jul 30, 2026Updated 2 weeks ago
- ☆224May 17, 2026Updated 2 months ago
- An experimental node☆574Feb 9, 2026Updated 6 months ago
- An enhanced Wan2.2 Image-to-Video node specifically designed to fix the slow-motion issue in 4-step LoRAs (like lightx2v).☆635Aug 1, 2026Updated 2 weeks ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- Comfyui implementation of OpenIXCLab Sec-4B☆373Dec 19, 2025Updated 7 months ago
- ☆58Dec 25, 2025Updated 7 months ago
- LR-Anchored Multi-Reward Preference Optimization for Generative Real-World Super-Resolution☆20Mar 20, 2026Updated 4 months ago
- A ComfyUI custom node that embeds a heavily-modified fork of Mesh2Motion as an interactive 3D editor directly inside a node.☆185May 8, 2026Updated 3 months ago
- A ComfyUI speech recognition plugin based on [Qwen3-ASR](https://github.com/QwenLM/Qwen3-ASR).☆37Feb 6, 2026Updated 6 months ago
- A simple node that can dynamically adjust the reserved memory of a workflow in real-time, used to avoid the utilization of shared memory.☆418Jul 4, 2026Updated last month
- Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.☆1,259Updated this week