[PR #2569] [CLOSED] Add QwenVL-Mod custom node to list #2602

New issue

Closed

opened 2026-10-28 21:11:06 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-28 21:11:06 +00:00

Owner

📋 Pull Request Information

Original PR: https://github.com/Comfy-Org/ComfyUI-Manager/pull/2569
Author: @huchukato
Created: 2/1/2026
Status: ❌ Closed

Base: main ← Head: main

📄 Description

🎯 Add QwenVL-Mod: Enhanced Vision-Language Custom Node
📋 Description
This PR adds the QwenVL-Mod custom node to the official ComfyUI Manager list. QwenVL-Mod is an advanced fork of the original QwenVL node with significant improvements and additional features for stable multimodal AI workflows.

✨ Key Features
🚀 Flash Attention 2: Enhanced performance and memory efficiency
🎬 WAN 2.2 Video Generation: Advanced video-to-video and image-to-video capabilities
🔓 Free Abliterated Models: Access to uncensored models for unrestricted workflows
🛡️ Comprehensive NSFW Support: Full support for mature content generation
⚡ Performance Optimizations: Major improvements over the original implementation
🏷️ Technical Details
Category: Image
Installation Type: Git Clone
Version: 2.0.4
Repository: https://github.com/huchukato/ComfyUI-QwenVL-Mod
📚 Tags
vision, language, multimodal, qwen, flash_attention, performance, wan2.2, video, i2v, t2v, abliterated, nsfw, enhanced, fork

🔍 Why Add This Node?
This node provides significant value to the ComfyUI community by offering:

Enhanced performance through Flash Attention 2
Advanced video generation capabilities
Unrestricted model access
Comprehensive feature set for professional workflows
The node is actively maintained and represents a substantial improvement over the base QwenVL implementation.

_{🔄 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/2569 **Author:** [@huchukato](https://github.com/huchukato) **Created:** 2/1/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `main` --- ### 📄 Description 🎯 Add QwenVL-Mod: Enhanced Vision-Language Custom Node 📋 Description This PR adds the QwenVL-Mod custom node to the official ComfyUI Manager list. QwenVL-Mod is an advanced fork of the original QwenVL node with significant improvements and additional features for stable multimodal AI workflows. ✨ Key Features 🚀 Flash Attention 2: Enhanced performance and memory efficiency 🎬 WAN 2.2 Video Generation: Advanced video-to-video and image-to-video capabilities 🔓 Free Abliterated Models: Access to uncensored models for unrestricted workflows 🛡️ Comprehensive NSFW Support: Full support for mature content generation ⚡ Performance Optimizations: Major improvements over the original implementation 🏷️ Technical Details Category: Image Installation Type: Git Clone Version: 2.0.4 Repository: https://github.com/huchukato/ComfyUI-QwenVL-Mod 📚 Tags vision, language, multimodal, qwen, flash_attention, performance, wan2.2, video, i2v, t2v, abliterated, nsfw, enhanced, fork 🔍 Why Add This Node? This node provides significant value to the ComfyUI community by offering: Enhanced performance through Flash Attention 2 Advanced video generation capabilities Unrestricted model access Comprehensive feature set for professional workflows The node is actively maintained and represents a substantial improvement over the base QwenVL implementation. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-28 21:11:06 +00:00