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。
☆129Jun 1, 2026Updated last month
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)☆102Jun 12, 2026Updated last month
- Comfy EverAnimate WIP☆17Jun 5, 2026Updated last month
- Pushing the Frontier of Long Video Generation Standalone, inference-only release for minute-level multi-shot audio-video generation with…☆57Jun 23, 2026Updated 3 weeks ago
- SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation☆39Mar 31, 2026Updated 3 months ago
- ☆444May 20, 2026Updated last month
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Standalone ComfyUI plugin for Wan 2.2 Bernini video generation and editing.☆130Updated this week
- ComfyUI custom nodes for LongCat-AudioDiT \ Diffusion-based Zero-Shot Text-to-Speech☆131Apr 4, 2026Updated 3 months ago
- This is a ComfyUI plug-in for https://github.com/Netflix/void-model☆18Apr 20, 2026Updated 2 months ago
- LTX Director and a variety of other custom ComfyUI nodes and workflows☆1,733Updated this week
- Seamless video connection and multi-reference image support for Wan Animate and Scail-2☆356Updated this week
- A ComfyUI custom node designed for LTX 2.3 MSR (Multiple-Subject-Reference) LoRA workflows.☆319Updated this week
- ComfyUI-AudioLoopHelper☆15Jul 5, 2026Updated last week
- The core component of Stand-In, the preprocessor, is essential—only images processed through it can fully unlock the capabilities of Stan…☆158Aug 21, 2025Updated 10 months ago
- ☆149Jun 27, 2026Updated 2 weeks ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Enhanced the comfyui savevideo node to support previewing and saving videos containing alpha channels.☆46Mar 11, 2026Updated 4 months ago
- An advanced Foveated Latent Sampler (FLS) for ComfyUI. Selective high-frequency local contrast boosting and stochastic texture noise inje…☆79May 21, 2026Updated last month
- ☆29May 27, 2026Updated last month
- Text-to-audio and video-to-audio using Sony AI's Woosh foundation model.☆119May 7, 2026Updated 2 months ago
- Vibe coded nodes for LTX2.3☆213Updated this week
- [ArXiv 26] EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration☆71Jun 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.☆1,098Updated this week
- ☆68Updated this week
- interpretability work and exploration for krea☆37Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- nunchaku0.3.0.dev2的各种轮子列表☆40May 20, 2025Updated last year
- a ComfyUI custom node for MultiTalk☆33Jun 18, 2025Updated last year
- A universal swap node that supports ComfyUI native workflow, allowing 4_6G users to experience Klein9B or other large models☆19Updated this week
- ☆26Jun 11, 2025Updated last year
- OmniShotCut is a sensitive and more informative SoTA on Shot Boundary Detection task.☆247Jun 1, 2026Updated last month
- Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning☆945Updated this week
- ComfyUI nodes for TencentARC Pixal3D image-to-3D generation☆26Jun 1, 2026Updated last month
- a ComfyyUI custom node for QwenImage Diffsynth☆72Aug 21, 2025Updated 10 months ago
- ☆117Jul 2, 2026Updated last week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captionin…☆149Aug 28, 2025Updated 10 months ago
- ☆204May 17, 2026Updated last month
- Training-free Krea2 style reference nodes for ComfyUI, with LoRA-like single-image transfer, experimental two-reference blending, low con…☆129Jul 7, 2026Updated last week
- A Conditioning Interpolation node in ComfyUI for using PixelSmile——一个用于在ComfyUI中使用PixelSmile项目的条件插值节点☆71Apr 1, 2026Updated 3 months ago
- ☆820Jan 24, 2026Updated 5 months ago
- An wrapper for Turbodiffusion to support 100-200x fast video generations.☆219Feb 10, 2026Updated 5 months ago
- Code for "OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation"☆149Jun 18, 2026Updated 3 weeks ago