comfyui-node

ComfyUI node for highly expressive speech and realistic zero-shot voice cloning

TBG Enhanced Tiled Upscaler and Refiner upscales up to 200MP with precise control. It features dual-model processing (structure + detail), per-pixel denoising to control where creativity is applied, and per-tile and per-object prompts, denoise, and seeds. Advanced fast previews. New generative tile fusion seamless joining, even on high-denoise.

ComfyUI custom node for NVIDIA PiD pixel diffusion decoding and upscale workflows

Split FLUX.2 and LTX 2.3 across two GPUs (LAN or same-machine) — NVENC compresses activations live on the wire. Icarus (ComfyUI node) + Daedalus (back-half server).

ComfyUI nodes to save time and keep your workflows tidy. Bundle multiple wires into one wire. Create customizable presets nodes.

Use your own API keys with ComfyUI. No account required.

Custom ComfyUI nodes to streamline and speed up workflows: multi-select and last-image loaders, pixel-art, model upscaling, batched VAE decode and a per-segment detailer; boolean AND/OR/NOT plus bypass/mute, pipe and bookmark nodes for clean branching; BBox-mask compositing; an rgthree-LoRA to Image-Saver bridge; and model-loader previews.

A ComfyUI custom node that uses GPT, Claude, Gemini, or local LLMs to enhance your rompts with 50+ artistic styles. Compatible with all FLux/SD models.

A Comfyui style explorer with the ability to add your own styles and a catalog where you can save previews generated in that style. you can create multiple catalogs so you can have a different catalog per image model. over 1000 built in styles!

Validated WanVideoWrapper workflows for SCAIL/SCAIL-2 RGB-driven animation, identity-aware masking, multi-person tracking, replacement conditioning and optional NLF pose processing.

Custom ComfyUI nodes and extensions

Try to locate the "orphan models" and clean them

ComfyUI

A battle-tested, TypeScript-first client for interacting with ComfyUI.

Node pack for ComfyUI + extension for Forge Neo providing an extensive color grading toolset for latents

Focused MiniMax-H3 multi-shot video nodes for ComfyUI. The Advance fork keeps the H3 long-form workflow focused: a small node surface, a unified loader, centralized controls, and a shot cache designed for fast iteration on multi-scene prompts.

Essential utility nodes for ComfyUI: Manage sequential prompt queues, automate complex camera angles, batch process text files, and select aspect-ratio correct resolutions effortlessly.

Two custom ComfyUI nodes that replace the default number widget with a styled, draggable slider and a prominent live value display.

Fastest Qwen3-TTS nodes for ComfyUI. CUDA graph capture for 5-8x faster generation, no quality loss. Voice cloning, voice design, batch. One-click install.

A studio rig for ComfyUI: one tabbed Workspace runs the whole image pipeline, from prompts and LoRAs to Paint with auto masks, Detailer, Post FX and Save, with a VRAM limit that keeps big rigs on small cards. Wireless control panels, plus Krea 2 moodboard and identity editing. 62 nodes, no pip dependencies.