Nathan aka SoCalGuitarist

ComfyUI-HiDream-Sampler. ComfyUI Wrapper for HiDream - 4bit linux loading fix

VibeVoice. Frontier Open-Source Text-to-Speech

scg_Foundation-1-comfyUI. ComfyUI nodes for RoyalCities Foundation-1 — structured text-to-sample music generation with full BPM, key, timbre, and FX control

OmniVoice-Manager. Modern non-Gradio web studio + API for OmniVoice zero-shot TTS: multi-speaker stitching, LUFS loudness matching, voice isolation/de-reverb, AI scriptwriter, and low-VRAM modes.

FramePack. Lets make video diffusion practical!

ComfyUI-Kontext-API. Nodes for interacting with Kontext API in ComfyUI

SCG_LocalVLM. ComfyUI QwenVL and Qwen wrapper

JoyAI-Image. JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

ComfyUI-SaveAudioMP3. quick Comfy Node to convert input waveform audio to MP3

ComfyUI-Soprano-TTS. Monkeypatched custom nodes for ComfyUI for supporting Soprano-TTS.

OmniGen2. OmniGen2: Unified Image Understanding and Generation.

DeepStereo. DeepStereo (Auto-autostereograms)

ComfyUI-DeepStereo. ComfyUI nodes for DeepStereo, an auto-autostereogram generator

fal-kontext-ui. Python

scg-utils. a collection of handy comfy nodes I find useful. YMMV.

scg_json_prompt_agent. ComfyUI custom node: visual JSON prompt builder + bbox layout editor with VLM/LLM agents (OpenAI-compatible, .env-configured).

scene-machine. TypeScript

omnivoice-manager-plugin-stable-audio-3. Stable Audio 3 (foley/SFX/music) plug-in for OmniVoice Manager — isolated sidecar, declarative UI, gated-model auto-download. Apache-2.0 code; model under Stability AI Community License.

scg-Cosmos3. ComfyUI wrapper nodes for NVIDIA Cosmos 3 omnimodal world models (text-to-image / text-to-video / image-to-video, with NF4 pre-quantized weights). Linux/DGX, bf16.

scg-NAVA. ComfyUI wrapper nodes for NAVA (ernie-research/NAVA): 6.3B Wan2.2-based joint audio+video generation.