[PR #2514] [MERGED] Add Halo-Lipsy: AMD unified memory lip sync node #2557

New issue

Closed

opened 2026-10-28 21:10:45 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-28 21:10:45 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/Comfy-Org/ComfyUI-Manager/pull/2514
Author: @bkpaine1
Created: 1/17/2026
Status: ✅ Merged
Merged: 1/20/2026
Merged by: @ltdrdata

Base: main ← Head: add-halo-lipsy

📝 Commits (1)

14d5f81 Add Halo-Lipsy: AMD unified memory lip sync node

📊 Changes

1 file changed (+12 additions, -1 deletions)

View changed files

📝 custom-node-list.json (+12 -1)

📄 Description

Summary

Adding Halo-Lipsy - a native Wav2Lip lip sync node that finally works on AMD APUs with unified memory.

Why This Node Exists

Existing lip sync nodes fail on AMD unified memory systems because they:

Use subprocess.run() which escapes the venv → library mismatches → crash
Write temporary files that end up as 0-byte "ghost files"
Try to cast vfloat16 tensors directly to NumPy → unified memory conflict
Auto-detect CUDA and fail without NVIDIA drivers

Halo-Lipsy fixes all of this:

Native Wav2Lip inference in the ComfyUI process (no subprocesses)
Face detection forced to CPU (prevents memory fighting)
Safe tensor casting: always .float().cpu().numpy()
Works with ROCm's CUDA translation layer

Features

Sync tuning (frame offset, mel timing multiplier)
Edge blending for clean face compositing
Adjustable face detection and smoothing
Force CPU mode for zero VRAM usage

Tested On

Ryzen AI Max+ 395 (Strix Halo) - 64GB unified memory
ROCm 7.11
ComfyUI with HunyuanVideo (15GB+) loaded simultaneously
Also works on NVIDIA/CUDA systems

Repository

https://github.com/bkpaine1/Halo-Lipsy

Credits

bkpaine1 - Testing, AMD hardware, bug hunting
Claude Code (Anthropic Opus 4.5) - Architecture & implementation
Wav2Lip - Original model by Rudrabha Mukhopadhyay

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/Comfy-Org/ComfyUI-Manager/pull/2514 **Author:** [@bkpaine1](https://github.com/bkpaine1) **Created:** 1/17/2026 **Status:** ✅ Merged **Merged:** 1/20/2026 **Merged by:** [@ltdrdata](https://github.com/ltdrdata) **Base:** `main` ← **Head:** `add-halo-lipsy` --- ### 📝 Commits (1) - [`14d5f81`](https://github.com/Comfy-Org/ComfyUI-Manager/commit/14d5f81058dbce55325014e8b82b598e684fbda4) Add Halo-Lipsy: AMD unified memory lip sync node ### 📊 Changes **1 file changed** (+12 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `custom-node-list.json` (+12 -1) </details> ### 📄 Description ## Summary Adding **Halo-Lipsy** - a native Wav2Lip lip sync node that finally works on AMD APUs with unified memory. ### Why This Node Exists Existing lip sync nodes fail on AMD unified memory systems because they: - Use `subprocess.run()` which escapes the venv → library mismatches → crash - Write temporary files that end up as 0-byte "ghost files" - Try to cast `vfloat16` tensors directly to NumPy → unified memory conflict - Auto-detect CUDA and fail without NVIDIA drivers **Halo-Lipsy fixes all of this:** - Native Wav2Lip inference in the ComfyUI process (no subprocesses) - Face detection forced to CPU (prevents memory fighting) - Safe tensor casting: always `.float().cpu().numpy()` - Works with ROCm's CUDA translation layer ### Features - Sync tuning (frame offset, mel timing multiplier) - Edge blending for clean face compositing - Adjustable face detection and smoothing - Force CPU mode for zero VRAM usage ### Tested On - **Ryzen AI Max+ 395 (Strix Halo)** - 64GB unified memory - **ROCm 7.11** - ComfyUI with HunyuanVideo (15GB+) loaded simultaneously - Also works on NVIDIA/CUDA systems ### Repository https://github.com/bkpaine1/Halo-Lipsy ### Credits - **bkpaine1** - Testing, AMD hardware, bug hunting - **Claude Code** (Anthropic Opus 4.5) - Architecture & implementation - **Wav2Lip** - Original model by Rudrabha Mukhopadhyay --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-28 21:10:45 +00:00