nodes/LevelPixel-ComfyUI-LevelPixel-Advanced
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated README.md

Browse Source
This commit is contained in:
Level Pixel Dev
2025-05-27 06:33:20 +06:00
parent fe2c65b56c
commit 52fa9318b9
1 changed files with 19 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+19 -20
View File
@@ -8,9 +8,11 @@ The purpose of this package is to collect the most necessary and atomic nodes fo
LLM nodes, LLaVa and other VLM nodes, Autotagger, RAM autotagger, WD Autotagger
Recommend that you install the main node package from Level Pixel:
[https://github.com/LevelPixel/ComfyUI-LevelPixel](https://github.com/LevelPixel/ComfyUI-LevelPixel)
The official repository of the current node package is located at this link:
[https://github.com/LevelPixel/ComfyUI-LevelPixel-Advanced](https://github.com/LevelPixel/ComfyUI-LevelPixel-Advanced)
## Contacts:
@@ -24,16 +26,18 @@ levelpixel.dev@gmail.com
Before running ComfyUI with this node package, you should make sure that you have the following programs and libraries installed so that ComfyUI can compile the necessary libraries and programs for llama-cpp-python (the main library that allows you to use any current GGUF models and neural network architectures):
* `CUDA drivers` - install the latest version.
Download: [https://developer.nvidia.com/cuda-downloads](https://developer.nvidia.com/cuda-downloads)
* `Visual Studio 2022 Community IDE` with libraries for compiling C++ programs, specifically with individual components (select them in Visual Studio Installer when installing/modifying Visual Studio 2022):
MSVC v143 - VS 2022 C++ x64/x86 build tools (Latest)
MSVC v143 - VS 2022 C++ x64/x86 build tools (v14.38-17.8)
C++ Cmake tools for Windows
C++ Cmake tools for Linux and Mac
Download: [https://visualstudio.microsoft.com/downloads](https://visualstudio.microsoft.com/downloads)
* `CMAKE official distribution` - download and install the latest version.
Download: [https://cmake.org/download](https://cmake.org/download)
1) `CUDA drivers` - install the latest version.
Download: [https://developer.nvidia.com/cuda-downloads](https://developer.nvidia.com/cuda-downloads)
2) `Visual Studio 2022 Community IDE` with libraries for compiling C++ programs, specifically with individual components (select them in Visual Studio Installer when installing/modifying Visual Studio 2022):
* MSVC v143 - VS 2022 C++ x64/x86 build tools (Latest)
* MSVC v143 - VS 2022 C++ x64/x86 build tools (v14.38-17.8)
* C++ Cmake tools for Windows
* C++ Cmake tools for Linux and Mac
Download: [https://visualstudio.microsoft.com/downloads](https://visualstudio.microsoft.com/downloads)
3) `CMAKE official distribution` - download and install the latest version.
Download: [https://cmake.org/download](https://cmake.org/download)
### Installation Using ComfyUI Manager (recommended):
@@ -63,7 +67,7 @@ If you have problems running ComfyUI with this node package, check and do the fo
* The path to Cmake (official distribution, for example, path `C:\Program Files\CMake\bin`) must be at the very top of the Path list in the **System environment variables**. Make sure that the path is at the top of the Path in the **System variables**, and not only in the user variables. If Cmake is not at the top of the list, then some libraries may not compile due to the lack of the current version of the Cmake compiler.
* The path to the current version of your CUDA must be at the very top of the **Path** list in the **System environment variables** (right after Cmake). Make sure that the path is at the top of the Path in the System variables, and not only in the user variables.
Here are the paths that should be in Path for CUDA (this is an example, substitute your CUDA version for "12.9"):
`C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\libnvvp`
`C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.9\bin`
* In System environment variables, add the `CMAKE_ARGS` variable and set it to the following:
@@ -106,20 +110,16 @@ The core functionality is taken from [ComfyUI_VLM_nodes](https://github.com/goka
How to use LLaVa nodes:
1. **Download the Qwen 2.5 VL gguf file**:
[https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main
](https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main)
[https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main](https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main)
Choose a gguf file **without** the mmproj in the name
Example gguf file:
[https://huggingface.co/Mungert/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-q8_0.gguf
](https://huggingface.co/Mungert/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-q8_0.gguf)
[https://huggingface.co/Mungert/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-q8_0.gguf](https://huggingface.co/Mungert/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-q8_0.gguf)
Copy this file to ComfyUI/model/Llavacheckpoint.
2. **Download the Qwen 2.5 VL mmproj file (this is clip model):**
[https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main
](https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main)
[https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main](https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/tree/main)
Choose a file **with** mmproj in the name
Example mmproj file:
[https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-mmproj-bf16.gguf
](https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-mmproj-bf16.gguf)
[https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-mmproj-bf16.gguf](https://huggingface.co/Mungert/Qwen2.5-VL-7B-Instruct-GGUF/resolve/main/Qwen2.5-VL-7B-Instruct-mmproj-bf16.gguf)
Copy this file to ComfyUI/model/Llavacheckpoint.
3. **Run ComfyUI and add to workflow node LLava Advanced [LP]. Choose ckpt model and clip, pin image and write prompt.**
@@ -162,4 +162,3 @@ RAM node for ComfyUI/[ComfyUI-Hangover-Recognize_Anything](https://github.com/Ha
Copyright (c) 2024-present [Level Pixel](https://github.com/LevelPixel)
Licensed under Apache License