Master ComfyUI
Workflows & Guides
The definitive tutorial hub for local AI creators. Master step-by-step video, 3D, image generation, and custom node workflows for production-ready AI pipelines.
Production Workflow Guides
Learn node routing, FLUX.1 architecture, custom Python development, and VRAM optimization techniques.
Complete Bernini-R ComfyUI Workflow Guide: Zero-LoRA In-Context Image & Video Editing
Step-by-step tutorial on running ByteDance's Bernini-R (Wan 2.2) natively in ComfyUI — covering Task Types (t2v, v2v, rv2v, img, ads2v), model installation, and zero-shot relighting.
Complete ERNIE-Image ComfyUI Workflow Guide: Standard vs. Turbo 8B DiT Setup & 3B Prompt Enhancer
Step-by-step tutorial on running Baidu's ERNIE-Image natively in ComfyUI — covering 8B DiT architecture, Standard (50-step) vs. Turbo (8-step), 3B Prompt Enhancer, and multilingual text rendering.
Complete Hunyuan3D-2 ComfyUI Workflow Guide: Single-View, Multi-View & Turbo 3D Mesh Generation
Step-by-step tutorial on running Tencent's Hunyuan3D 2.0 natively in ComfyUI — covering Single-View, Multi-View, and Turbo 3D geometry mesh generation (.glb) and checkpoint setup.
Popular Custom Nodes
Extend ComfyUI capability with motion modules, IPAdapter, and high-resolution tile upscalers.
Audio Separation Nodes
Audio source separation node suite employing Demucs models to split vocal, drum, bass, and instrumental stems for video audio sync.
Audio vocal/drum stem separation via Demucs for audio-reactive AI video
Use Everywhere
Wireless connection nodes automatically broadcasting inputs across matching data types without cluttering canvas wires.
Wireless node connections and clean workflow canvas organization
ComfyUI CLIPtion
Automated image captioning and prompt interrogator node utilizing CLIP and BLIP models for dataset tagging.
Automated image captioning & dataset tagging via CLIP/BLIP
Featured Models & LoRAs
Optimized UNet checkpoints and LoRA adapters ready for FLUX.1 and SDXL pipelines.
AI Hands XL
Specialized SDXL negative/positive conditioning LoRA fixing extra fingers, fused thumbs, and awkward hand positioning.
Eliminating extra fingers & fused thumbs in SDXL portraits
aidmaNSFWunlock (FLUX Unlock LoRA)
Popular FLUX.1 prompt guidance unlocking LoRA expanding anatomical and figure drawing freedom in FLUX generations.
Unlocking anatomical figure drawing freedom for FLUX.1
ByteDance Hyper-FLUX Acceleration LoRA
ByteDance 8-step / 16-step Hyper-SD acceleration LoRA for FLUX.1 models cutting inference time by 75%.
8-step / 16-step ultra-fast FLUX.1 inference acceleration
Ready to Level Up Your ComfyUI Workflows?
Browse step-by-step FLUX.1 guides, Python custom node APIs, and VRAM optimization techniques created by the AI creator community.