Stars
ComfyUI 节点「资产卡」+「资产卡 to Director Group」：把图/音/描述组成的资产卡直接喂给 MiniMax H3 导演台分段；含单端口多连线、选中高亮上游、提示词富文本编辑器。示例工作流见 example_workflows/
The easiest way to use MiniMax H3. One compact workflow for T2V, I2V, first/last-frame, and reference video generation, with a unified multi-media input, powerful @ references, and inline dialogue …
A custom node set for Video Frame Interpolation in ComfyUI.
Use local Qwen3.8-27B and official MiniMax-H3 Skills in ComfyUI to generate H3 prompts. Runs a standalone local llama-server , inference operates fully offline with no internet access.
Multi-segment MiniMax H3 Director for official ComfyUI MiniMax-H3
ComfyUI custom nodes for DLSS 5 Neural Video & Image Enhancer with Frame Interpolation
Experimental test to freeze video latents while continuing with audio processing, to increase audio quality in low-step turbo MiniMax H3 generations
Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins
Neural latent upscaler for Minimax H3 (24ch). Bypasses costly 5B-param VAE decode/encode. Upscale low-res latents directly, then refine. Accelerates high-res video gen, outperforms naive interp.
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
A universal swap node that supports ComfyUI native workflow, allowing 4_6G users to experience Klein9B or other large models
Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).
Instruction-based, identity-preserving image editing for Krea 2 in ComfyUI — nodes + workflows for the Krea 2 Identity Edit LoRA
Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.
Quality-preserving per-layer conditioning control for Krea 2 (ComfyUI node). Fork of nova452/ComfyUI-ConditioningKrea2Rebalance — RMS renormalization + presets, defaults that don't destabilize the …
Standalone ComfyUI plugin for Wan 2.2 Bernini video generation and editing.
A ComfyUI custom node designed for LTX 2.3 MSR (Multiple-Subject-Reference) LoRA workflows.
A ComfyUI custom node package for streamlined media loading and video pipeline assembly. Provides intuitive nodes that simplify media resource loading with user-friendly parameters, making it easie…
JoyAI-Echo-1.5: Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds
Pushing the Frontier of Long Video Generation Standalone, inference-only release for minute-level multi-shot audio-video generation with a distilled DMD generator, paired cross-modal memory, and st…
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…
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.