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。
☆160Jun 1, 2026Updated 5 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)☆140Jun 12, 2026Updated 4 months ago
- Pushing the Frontier of Long Video Generation Standalone, inference-only release for minute-level multi-shot audio-video generation with…☆57Sep 16, 2026Updated last month
- Comfy EverAnimate WIP☆18Updated this week
- MiniMaxH3_LatentUpscaler for ComfyUI☆38Sep 21, 2026Updated last month
- SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation☆41Updated this week
- 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.
- ☆493May 20, 2026Updated 5 months ago
- Standalone ComfyUI plugin for Wan 2.2 Bernini video generation and editing.☆136Sep 10, 2026Updated last month
- A ComfyUI custom node designed for LTX 2.3 MSR (Multiple-Subject-Reference) LoRA workflows.☆380Jul 14, 2026Updated 3 months ago
- ComfyUI custom nodes for DLSS 5 Neural Video & Image Enhancer with Frame Interpolation☆141Sep 17, 2026Updated last month
- ComfyUI custom nodes for LongCat-AudioDiT \ Diffusion-based Zero-Shot Text-to-Speech☆142Apr 4, 2026Updated 7 months ago
- Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. …☆823Sep 17, 2026Updated last month
- 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.☆50Feb 28, 2026Updated 8 months ago
- ComfyUI custom nodes for Fish Audio S2-Pro TTS — voice clone, multi-speaker, and text-to-speech☆307Apr 27, 2026Updated 6 months ago
- LTX Director and a variety of other custom ComfyUI nodes and workflows☆2,093Jul 30, 2026Updated 3 months 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.
- ☆756Oct 15, 2026Updated 3 weeks ago
- Vibe coded nodes for LTX2.3☆251Jul 30, 2026Updated 3 months ago
- Use local Qwen3.8-27B and official MiniMax-H3 Skills in ComfyUI to generate H3 prompts. Runs a standalone local llama-server , inference …☆145Oct 28, 2026Updated last week
- A universal swap node that supports ComfyUI native workflow, allowing 4_6G users to experience Klein9B or other large models☆149Sep 11, 2026Updated last month
- ☆406Sep 18, 2026Updated last month
- This is a ComfyUI plug-in for https://github.com/Netflix/void-model☆18Apr 20, 2026Updated 6 months ago
- ComfyUI nodes for SCAIL-Pose preprocessing☆325Apr 15, 2026Updated 6 months ago
- Seamless video connection and multi-reference image support for Wan Animate,Scail-2 and Wan Animate2☆426Sep 14, 2026Updated last month
- MatAnyone in ComfyUI☆107Mar 15, 2026Updated 7 months ago
- 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.
- Training-free Krea2 style reference nodes for ComfyUI, with LoRA-like single-image transfer, experimental two-reference blending, low con…☆246Jul 21, 2026Updated 3 months ago
- This is a ComfyUI plug-in for https://github.com/KlingTeam/UniVideo☆38Jan 19, 2026Updated 9 months ago
- ☆12Aug 17, 2026Updated 2 months ago
- Mel-Band RoFormer for Music Source Separation☆263Jan 30, 2026Updated 9 months ago
- MatlowAI's MiniMax-H3 ComfyUI nodes: Contact-Sheet diffusion + Motion Lab (test-time de-roping of fast motion)☆236Updated this week
- ☆136Updated this week
- ☆170Jun 27, 2026Updated 4 months ago
- A custom ComfyUI node for MiniCPM vision-language models, supporting v4, v4.5, and v4 GGUF formats, enabling high-quality image captionin…☆156Aug 28, 2025Updated last year
- ComfyUI SAM3 node based on transformers / 基于 transformers 框架的 SAM3分割节点☆21Jan 29, 2026Updated 9 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- A set of nodes in ComfyUI, developed for video workflows☆83Oct 29, 2026Updated last week
- ComfyUI workflow for MiniMax-H3-Turbo☆16Oct 23, 2026Updated 2 weeks ago
- Training-free Spectrum acceleration for ComfyUI’s native MiniMax H3 audio-video model. Uses Chebyshev ridge feature forecasting to skip s…☆714Updated this week
- H3-aware latent upscaling for ComfyUI with automatic 32-pixel alignment.☆25Aug 17, 2026Updated 2 months ago
- ☆32May 27, 2026Updated 5 months ago
- Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.☆1,357Aug 13, 2026Updated 2 months ago
- ☆390Updated this week