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

First commit

Browse Source
This commit is contained in:
Level Pixel Dev
2025-05-24 00:57:31 +06:00
commit 28d99ae570
13 changed files with 1247 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.gitignore
+1
View File
@@ -0,0 +1 @@
__pycache__
LICENSE
+211
View File
@@ -0,0 +1,211 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
10. Additional information and licenses (but not excluding all of
the above):
The developers and contributors to this product and repository
do not bear any responsibility for any damage or loss of your data,
valuables, passwords, accounts and any other things that could be
damaged, distorted, damaged, lost, stolen due to the use of this
software and information files. The developers and contributors
to this product do not bear any responsibility for the violation
of your privacy and anonymity.
Use the code, scripts and programs from this repository at your
own risk, all responsibility for the use and launch of the program
code is entirely yours.
Level Pixel has no malicious intent in developing its products,
any problems and violations that you experience are either your
fault or the fault of third parties (the owners of those software
packages that you automatically download along with this product
and program code). Level Pixel does not sell this code, and the
original materials on which these files and program code were
created belong to their rightful owners, as indicated in their
licenses.
END OF TERMS AND CONDITIONS
Copyright Level Pixel
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
README.md
+70
View File
@@ -0,0 +1,70 @@
## Level Pixel nodes for ComfyUI - Advanced nodes
![banner_LevelPixel_with_logo](https://github.com/user-attachments/assets/ef79f2c9-04fb-485f-aba5-6cd00cb14d8c)
The purpose of this package is to collect the most necessary and atomic nodes for working with LLM and VLM models.
**In this Level Pixel Advanced node pack you will find:**
LLM nodes, LLaVa and other VLM nodes
## Contacts:
For cooperation, suggestions and ideas you can write to email:
levelpixel.dev@gmail.com
# Installation:
## Installation Using ComfyUI Manager (recommended):
Install [ComfyUI Manager](https://github.com/ltdrdata/ComfyUI-Manager) and do steps introduced there to install this repo 'ComfyUI-LevelPixel-Advanced'.
The nodes of the current package will be updated automatically when you click "Update ALL" in ComfyUI Manager.
## Alternative installation:
Clone the repository:
`git clone https://github.com/LevelPixel/ComfyUI-LevelPixel-Advanced.git`
to your ComfyUI `custom_nodes` directory
The script will then automatically install all custom scripts and nodes.
It will attempt to use symlinks and junctions to prevent having to copy files and keep them up to date.
- For uninstallation:
- Delete the cloned repo in `custom_nodes`
- Ensure `web/extensions/levelpixel` has also been removed
- For manual update:
- Navigate to the cloned repo e.g. `custom_nodes/ComfyUI-LevelPixel`
- `git pull`
# Features
All nodes Level Pixel:
<img width="1171" alt="level-pixel-nodes_2" src="https://github.com/user-attachments/assets/e3b183b1-23d8-4d8b-bd7f-fae00c6a488c">
## LLM nodes
A node that generates text using the LLM model with subsequent unloading of the model from memory. Useful in those workflows where there is constant switching between different models and technologies under conditions of insufficient RAM of the video processor.
Our LLM nodes support the latest LLM and CLIP models, and should support future ones (please let us know if any models stop working).
The core functionality is taken from [ComfyUI_VLM_nodes](https://github.com/gokayfem/ComfyUI_VLM_nodes) and belongs to its authors.
## LLaVa nodes
A node that generates text using the LLM model and CLIP by image and prompt with subsequent unloading of the model from memory.
Our LLava nodes support the latest LLM models, and should support future ones (please let us know if any models stop working).
The core functionality is taken from [ComfyUI_VLM_nodes](https://github.com/gokayfem/ComfyUI_VLM_nodes) and belongs to its authors.
# Credits
ComfyUI/[ComfyUI](https://github.com/comfyanonymous/ComfyUI) - A powerful and modular stable diffusion GUI.
VLM nodes for ComfyUI/[ComfyUI_VLM_nodes](https://github.com/gokayfem/ComfyUI_VLM_nodes) - Best VLM nodes for ComfyUI.
# License
Copyright (c) 2024-present [Level Pixel](https://github.com/LevelPixel)
Licensed under Apache License
__init__.py
+52
View File
@@ -0,0 +1,52 @@
import os
import pkg_resources
import sys
import subprocess
import importlib
def check_requirements_installed(requirements_path):
with open(requirements_path, 'r') as f:
requirements = [pkg_resources.Requirement.parse(line.strip()) for line in f if line.strip()]
installed_packages = {pkg.key: pkg for pkg in pkg_resources.working_set}
installed_packages_set = set(installed_packages.keys())
missing_packages = []
for requirement in requirements:
if requirement.key not in installed_packages_set or not installed_packages[requirement.key] in requirement:
missing_packages.append(str(requirement))
if missing_packages:
print(f"Missing or outdated packages: {', '.join(missing_packages)}")
print("Installing/Updating missing packages...")
subprocess.check_call([sys.executable, '-s', '-m', 'pip', 'install', *missing_packages])
else:
print("All packages from requirements.txt are installed and up to date.")
requirements_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "requirements.txt")
check_requirements_installed(requirements_path)
from .install_init import init, get_system_info, install_llama
system_info = get_system_info()
install_llama(system_info)
llama_cpp_agent_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "cpp_agent_req.txt")
check_requirements_installed(llama_cpp_agent_path)
init()
node_list = [
"llm.llm_LP",
"vlm.llava_LP",
]
NODE_CLASS_MAPPINGS = {}
NODE_DISPLAY_NAME_MAPPINGS = {}
for module_name in node_list:
imported_module = importlib.import_module(f".nodes.{module_name}", __name__)
NODE_CLASS_MAPPINGS = {**NODE_CLASS_MAPPINGS, **imported_module.NODE_CLASS_MAPPINGS}
NODE_DISPLAY_NAME_MAPPINGS = {**NODE_DISPLAY_NAME_MAPPINGS, **imported_module.NODE_DISPLAY_NAME_MAPPINGS}
WEB_DIRECTORY = "./web"
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS", "WEB_DIRECTORY"]
cpp_agent_req.txt
+5
View File
@@ -0,0 +1,5 @@
llama-cpp-agent
mkdocs
mkdocs-material
mkdocstrings[python]
docstring-parser
install_init.py
+340
View File
@@ -0,0 +1,340 @@
import os
import json
import shutil
import platform
import subprocess
import sys
import importlib.util
import re
import inspect
from requests import get
from server import PromptServer
def verify_python_support():
version = tuple(map(int, platform.python_version_tuple()[:2]))
if version < (3, 8):
print("Warning: Python 3.8 or higher is required")
return False
return True
def verify_pypy_support(system_info):
if 'pp' in system_info['python_version']:
pp_ver = system_info['python_version'][2:4]
if pp_ver not in ['38', '39', '310']:
print("Warning: Current PyPy version may not be supported")
return False
if system_info['platform_tag'] not in ['linux_i686', 'linux_x86_64', 'win_amd64',
'macosx_10_15_x86_64', 'macosx_10_9_x86_64']:
print("Warning: Current platform may not be supported for PyPy")
return False
return True
def get_python_version():
version_match = re.match(r"3\.(\d+)", platform.python_version())
if version_match:
return "3" + version_match.group(1)
else:
return None
def get_system_info():
system_info = {
'gpu': False,
'cuda_version': None,
'rocm_version': None,
'python_version': get_python_version(),
'os': platform.system().lower(),
'arch': platform.machine().lower(),
'platform_tag': None
}
# Determine platform-specific tags
if system_info['os'] == 'linux':
if system_info['arch'] == 'x86_64':
system_info['platform_tag'] = 'linux_x86_64'
elif system_info['arch'] == 'i686':
system_info['platform_tag'] = 'linux_i686'
elif system_info['arch'] == 'aarch64':
system_info['platform_tag'] = 'linux_aarch64'
elif system_info['os'] == 'windows':
if system_info['arch'] == 'amd64':
system_info['platform_tag'] = 'win_amd64'
elif system_info['arch'] == 'x86':
system_info['platform_tag'] = 'win32'
elif system_info['os'] == 'darwin':
if system_info['arch'] == 'x86_64':
# Intel Mac
if 'pp' in system_info['python_version']:
system_info['platform_tag'] = 'macosx_10_15_x86_64'
else:
py_ver = int(system_info['python_version'][3:])
if py_ver >= 12:
system_info['platform_tag'] = 'macosx_10_13_x86_64'
else:
system_info['platform_tag'] = 'macosx_10_9_x86_64'
elif system_info['arch'] == 'arm64':
# Apple Silicon (M1/M2/M3)
print("Apple Silicon detected. llama-cpp-python will be built with Metal support")
system_info['platform_tag'] = None # Force source build for optimal Metal support
system_info['metal'] = True
# Check for GPU support
if importlib.util.find_spec('torch'):
try:
import torch
if hasattr(torch.version, 'hip') and torch.version.hip is not None:
system_info['gpu'] = True
system_info['rocm_version'] = f"rocm{torch.version.hip}"
elif torch.cuda.is_available():
system_info['gpu'] = True
system_info['cuda_version'] = "cu" + torch.version.cuda.replace(".", "").strip()
except:
pass
return system_info
def latest_lamacpp():
try:
response = get("https://api.github.com/repos/abetlen/llama-cpp-python/releases/latest")
return response.json()["tag_name"].replace("v", "")
except Exception:
return "0.2.20"
def install_package(package_name, extra_args=None):
command = [sys.executable, "-m", "pip", "install", package_name, "--no-cache-dir"]
if extra_args:
command.extend(extra_args.split())
subprocess.check_call(command)
def package_is_installed(package_name):
return importlib.util.find_spec(package_name) is not None
def install_llama(system_info):
if not verify_python_support():
print("ERROR: Unsupported Python version")
return False
if not verify_pypy_support(system_info):
print("WARNING: Unsupported PyPy configuration")
imported = package_is_installed("llama-cpp-python") or package_is_installed("llama_cpp")
if imported:
print("llama-cpp installed")
return True
# Simple pip install for Linux
if system_info['os'] == 'linux':
try:
print("Installing llama-cpp-python via pip")
install_package("llama-cpp-python")
return True
except Exception as e:
print(f"Installation failed: {e}")
return False
# If pre-built wheels fail, try GitHub release wheels
try:
version = latest_lamacpp()
platform_tag = system_info['platform_tag']
if platform_tag:
python_version = system_info['python_version']
wheel_name = f"llama_cpp_python-{version}-{python_version}-{python_version}-{platform_tag}.whl"
wheel_url = f"https://github.com/abetlen/llama-cpp-python/releases/download/v{version}/{wheel_name}"
print(f"Attempting to install from {wheel_url}")
install_package(wheel_url)
print(f"Successfully installed llama-cpp-python v{version}")
return True
except Exception as e:
print(f"GitHub wheel installation failed: {e}")
print("Attempting source build with acceleration...")
# Build from source with appropriate acceleration
try:
if system_info.get('metal', False):
print("Building llama-cpp-python from source with Metal support")
os.environ['CMAKE_ARGS'] = "-DGGML_METAL=on"
install_package("llama-cpp-python")
return True
elif system_info['gpu']:
if system_info.get('cuda_version'):
print("Building llama-cpp-python from source with CUDA support")
# Add ZLUDA support check
if os.environ.get('ZLUDA_PATH'):
print("ZLUDA detected, building with ZLUDA support")
os.environ['CMAKE_ARGS'] = "-DGGML_CUDA=on -DGGML_CUDA_ZLUDA=on"
else:
os.environ['CMAKE_ARGS'] = "-DGGML_CUDA=on"
install_package("llama-cpp-python")
return True
elif system_info.get('rocm_version'):
print("Building llama-cpp-python from source with ROCm support")
os.environ['CMAKE_ARGS'] = "-DGGML_HIPBLAS=on"
install_package("llama-cpp-python")
return True
except Exception as e:
print(f"Accelerated build failed: {e}")
print("Falling back to CPU-only version")
# Final fallback - basic CPU version
try:
print("Installing CPU-only version")
install_package("llama-cpp-python")
return True
except Exception as e:
print(f"CPU installation failed: {e}")
return False
config = None
def is_logging_enabled():
config = get_extension_config()
if "logging" not in config:
return False
return config["logging"]
def log(message, type=None, always=False, name=None):
if not always and not is_logging_enabled():
return
if type is not None:
message = f"[{type}] {message}"
if name is None:
name = get_extension_config()["name"]
print(f"(levelpixel-nodes:{name}) {message}")
def get_ext_dir(subpath=None, mkdir=False):
dir = os.path.dirname(__file__)
if subpath is not None:
dir = os.path.join(dir, subpath)
dir = os.path.abspath(dir)
if mkdir and not os.path.exists(dir):
os.makedirs(dir)
return dir
def get_extension_config(reload=False):
global config
if reload == False and config is not None:
return config
config_path = get_ext_dir("levelpixel.json")
default_config_path = get_ext_dir("levelpixel.default.json")
if not os.path.exists(config_path):
if os.path.exists(default_config_path):
shutil.copy(default_config_path, config_path)
if not os.path.exists(config_path):
log(f"Failed to create config at {config_path}", type="ERROR", always=True, name="???")
print(f"Extension path: {get_ext_dir()}")
return {"name": "Unknown", "version": -1}
else:
log("Missing levelpixel.default.json, this extension may not work correctly. Please reinstall the extension.",
type="ERROR", always=True, name="???")
print(f"Extension path: {get_ext_dir()}")
return {"name": "Unknown", "version": -1}
with open(config_path, "r") as f:
config = json.loads(f.read())
return config
def link_js(src, dst):
src = os.path.abspath(src)
dst = os.path.abspath(dst)
if os.name == "nt":
try:
import _winapi
_winapi.CreateJunction(src, dst)
return True
except:
pass
try:
os.symlink(src, dst)
return True
except:
import logging
logging.exception('')
return False
def is_junction(path):
if os.name != "nt":
return False
try:
return bool(os.readlink(path))
except OSError:
return False
def install_js():
src_dir = get_ext_dir("web/js")
if not os.path.exists(src_dir):
log("No JS")
return
should_install = should_install_js()
if should_install:
log("it looks like you're running an old version of ComfyUI that requires manual setup of web files, it is recommended you update your installation.", "warning", True)
dst_dir = get_web_ext_dir()
linked = os.path.islink(dst_dir) or is_junction(dst_dir)
if linked or os.path.exists(dst_dir):
if linked:
if should_install:
log("JS already linked")
else:
os.unlink(dst_dir)
log("JS unlinked, PromptServer will serve extension")
elif not should_install:
shutil.rmtree(dst_dir)
log("JS deleted, PromptServer will serve extension")
return
if not should_install:
log("JS skipped, PromptServer will serve extension")
return
if link_js(src_dir, dst_dir):
log("JS linked")
return
log("Copying JS files")
shutil.copytree(src_dir, dst_dir, dirs_exist_ok=True)
def get_web_ext_dir():
config = get_extension_config()
name = config["name"]
dir = get_comfy_dir("web/extensions/levelpixel")
if not os.path.exists(dir):
os.makedirs(dir)
dir = os.path.join(dir, name)
return dir
def get_comfy_dir(subpath=None, mkdir=False):
dir = os.path.dirname(inspect.getfile(PromptServer))
if subpath is not None:
dir = os.path.join(dir, subpath)
dir = os.path.abspath(dir)
if mkdir and not os.path.exists(dir):
os.makedirs(dir)
return dir
def should_install_js():
return not hasattr(PromptServer.instance, "supports") or "custom_nodes_from_web" not in PromptServer.instance.supports
def init(check_imports=None):
log("Init")
if check_imports is not None:
import importlib.util
for imp in check_imports:
spec = importlib.util.find_spec(imp)
if spec is None:
log(f"{imp} is required, please check requirements are installed.",
type="ERROR", always=True)
return False
install_js()
return True
levelpixel.default.json
+4
View File
@@ -0,0 +1,4 @@
{
"name": "LevelPixelAdvanced",
"logging": false
}
levelpixel.json
+4
View File
@@ -0,0 +1,4 @@
{
"name": "LevelPixelAdvanced",
"logging": false
}
node_list.json
+11
View File
@@ -0,0 +1,11 @@
{
"LLM Loader [LP]":"Loads a large language model specified by the user. Models are stored in the LLavacheckpoints folder.",
"LLM Sampler [LP]":"Generates text using the LLM. Simple settings.",
"LLM Advanced [LP]":"Generates text using the LLM. Advanced settings.",
"LLava Loader [LP]":"Loads a visual large language model specified by the user. Models are stored in the LLavacheckpoints folder.",
"LLava Clip Loader [LP]":"Loads a CLIP model specified by the user for VLM model. Models are stored in the LLavacheckpoints folder.",
"LLava Sampler Simple [LP]":"Generates text using the VLM. Simple settings.",
"LLava Sampler Advanced [LP]":"Generates text using the VLM. Advanced settings.",
"LLava Simple [LP]":"Generates text using the loaded VLM from LLava Loader. Simple settings.",
"LLava Advanced [LP]":"Generates text using the loaded VLM from LLava Loader. Advanced settings."
}
nodes/llm/llm_LP.py
+163
View File
@@ -0,0 +1,163 @@
import folder_paths
import os
from llama_cpp import Llama
import gc
import torch
supported_LLava_extensions = set(['.gguf'])
try:
folder_paths.folder_names_and_paths["LLavacheckpoints"] = (folder_paths.folder_names_and_paths["LLavacheckpoints"][0], supported_LLava_extensions)
except:
if not os.path.isdir(os.path.join(folder_paths.models_dir, "LLavacheckpoints")):
os.mkdir(os.path.join(folder_paths.models_dir, "LLavacheckpoints"))
folder_paths.folder_names_and_paths["LLavacheckpoints"] = ([os.path.join(folder_paths.models_dir, "LLavacheckpoints")], supported_LLava_extensions)
class LLMLoader:
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"ckpt_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
"max_ctx": ("INT", {"default": 2048, "min": 128, "max": 128000, "step": 64}),
"gpu_layers": ("INT", {"default": 27, "min": 0, "max": 100, "step": 1}),
"n_threads": ("INT", {"default": 8, "min": 1, "max": 100, "step": 1}),
}
}
RETURN_TYPES = ("CUSTOM",)
RETURN_NAMES = ("model",)
FUNCTION = "load_llm_checkpoint"
CATEGORY = "LevelPixel/LLM"
def load_llm_checkpoint(self, ckpt_name, max_ctx, gpu_layers, n_threads):
ckpt_path = folder_paths.get_full_path("LLavacheckpoints", ckpt_name)
llm = Llama(model_path = ckpt_path, chat_format="chatml", offload_kqv=True,
f16_kv=True, use_mlock=False, embedding=False, n_batch=1024,
last_n_tokens_size=1024, verbose=True, seed=42, n_ctx = max_ctx,
n_gpu_layers=gpu_layers, n_threads=n_threads,)
return (llm, )
class LLMSampler:
def __init__(self):
pass
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"model": ("CUSTOM", {"default": ""}),
"max_tokens": ("INT", {"default": 512, "min": 1, "max": 2048, "step": 1}),
"temperature": ("FLOAT", {"default": 0.2, "min": 0.01, "max": 1.0, "step": 0.01}),
"top_p": ("FLOAT", {"default": 0.95, "min": 0.1, "max": 1.0, "step": 0.01}),
"top_k": ("INT", {"default": 40, "step": 1}),
"frequency_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"presence_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"repeat_penalty": ("FLOAT", {"default": 1.1, "step": 0.01}),
"seed": ("INT", {"default": 42, "step": 1}),
"prompt": ("STRING",{"multiline": True, "default": ""}),
"system_msg": ("STRING",{ "multiline": True, "default" : "You are an assistant who perfectly describes images."}),
}
}
RETURN_TYPES = ("STRING",)
FUNCTION = "generate_text_sampler"
CATEGORY = "LevelPixel/LLM"
def generate_text_sampler(self, system_msg, prompt, model, max_tokens,
temperature, top_p, top_k, frequency_penalty,
presence_penalty, repeat_penalty, seed):
llm = model
response = llm.create_chat_completion(messages=[
{"role": "system", "content": system_msg},
{"role": "user", "content": prompt + " Assistant:"},
],
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
top_k=top_k,
frequency_penalty=frequency_penalty,
presence_penalty=presence_penalty,
repeat_penalty=repeat_penalty,
seed=seed
)
return (f"{response['choices'][0]['message']['content']}", )
class LLMAdvanced:
def __init__(self):
self.llm = None
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"ckpt_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
"max_ctx": ("INT", {"default": 2048, "min": 300, "max": 100000, "step": 64}),
"gpu_layers": ("INT", {"default": 27, "min": 0, "max": 100, "step": 1}),
"n_threads": ("INT", {"default": 8, "min": 1, "max": 100, "step": 1}),
"max_tokens": ("INT", {"default": 512, "min": 1, "max": 2048, "step": 1}),
"temperature": ("FLOAT", {"default": 0.1, "min": 0.01, "max": 1.0, "step": 0.01}),
"top_p": ("FLOAT", {"default": 0.95, "min": 0.1, "max": 1.0, "step": 0.01}),
"top_k": ("INT", {"default": 40, "step": 1}),
"frequency_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"presence_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"repeat_penalty": ("FLOAT", {"default": 1.1, "step": 0.01}),
"seed": ("INT", {"default": 42, "step": 1}),
"unload": ("BOOLEAN", {"default": False}),
"prompt": ("STRING", {"multiline": True, "default": ""}),
"system_msg": ("STRING", {"multiline": True, "default": "You are an assistant who perfectly describes images."}),
}
}
RETURN_TYPES = ("STRING",)
FUNCTION = "generate_text_advanced"
CATEGORY = "LevelPixel/LLM"
def generate_text_advanced(self, ckpt_name, max_ctx, gpu_layers, n_threads,
system_msg, prompt, max_tokens, temperature, top_p,
top_k, frequency_penalty, presence_penalty, repeat_penalty, seed, unload):
ckpt_path = folder_paths.get_full_path("LLavacheckpoints", ckpt_name)
self.llm = Llama(model_path = ckpt_path, offload_kqv=True, f16_kv=True,
use_mlock=False, embedding=False, n_batch=1024, last_n_tokens_size=1024,
verbose=True, seed=42, n_ctx = max_ctx, n_gpu_layers=gpu_layers,
n_threads=n_threads, logits_all=True, echo=False)
response = self.llm.create_chat_completion(messages=[
{"role": "system", "content": system_msg},
{"role": "user", "content": prompt},
],
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
top_k=top_k,
frequency_penalty=frequency_penalty,
presence_penalty=presence_penalty,
repeat_penalty=repeat_penalty,
seed=seed,
)
if unload and self.llm is not None:
self.llm.close()
del self.llm
self.llm = None
gc.collect()
torch.cuda.empty_cache()
return (f"{response['choices'][0]['message']['content']}", )
NODE_CLASS_MAPPINGS = {
"LLMLoader|LP": LLMLoader,
"LLMSampler|LP": LLMSampler,
"LLMAdvanced|LP": LLMAdvanced,
}
NODE_DISPLAY_NAME_MAPPINGS = {
"LLMLoader|LP": "LLM Loader [LP]",
"LLMSampler|LP": "LLM Sampler [LP]",
"LLMAdvanced|LP": "LLM Advanced [LP]"
}
nodes/vlm/llava_LP.py
+367
View File
@@ -0,0 +1,367 @@
import folder_paths
import os
from io import BytesIO
from llama_cpp import Llama
from llama_cpp.llama_chat_format import Llava16ChatHandler
import base64
from torchvision.transforms import ToPILImage
import gc
import torch
supported_LLava_extensions = set(['.gguf'])
try:
folder_paths.folder_names_and_paths["LLavacheckpoints"] = (folder_paths.folder_names_and_paths["LLavacheckpoints"][0], supported_LLava_extensions)
except:
if not os.path.isdir(os.path.join(folder_paths.models_dir, "LLavacheckpoints")):
os.mkdir(os.path.join(folder_paths.models_dir, "LLavacheckpoints"))
folder_paths.folder_names_and_paths["LLavacheckpoints"] = ([os.path.join(folder_paths.models_dir, "LLavacheckpoints")], supported_LLava_extensions)
class LLavaLoader:
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"ckpt_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
"max_ctx": ("INT", {"default": 4096, "min": 128, "max": 8192, "step": 64}),
"gpu_layers": ("INT", {"default": 27, "min": 0, "max": 100, "step": 1}),
"n_threads": ("INT", {"default": 8, "min": 1, "max": 100, "step": 1}),
"clip": ("CUSTOM", {"default": ""}),
}
}
RETURN_TYPES = ("CUSTOM",)
RETURN_NAMES = ("model",)
FUNCTION = "load_llava_checkpoint"
CATEGORY = "LevelPixel/VLM"
def load_llava_checkpoint(self, ckpt_name, max_ctx, gpu_layers, n_threads, clip ):
ckpt_path = folder_paths.get_full_path("LLavacheckpoints", ckpt_name)
llm = Llama(model_path = ckpt_path, chat_handler=clip,offload_kqv=True, f16_kv=True,
use_mlock=False, embedding=False, n_batch=1024, last_n_tokens_size=1024,
verbose=True, seed=42, n_ctx = max_ctx, n_gpu_layers=gpu_layers, n_threads=n_threads,
logits_all=True, echo=False)
return (llm, )
class LLavaClipLoader:
@classmethod
def INPUT_TYPES(s):
return {
"required": {
"clip_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
}
}
RETURN_TYPES = ("CUSTOM", )
RETURN_NAMES = ("clip", )
FUNCTION = "load_clip_checkpoint"
CATEGORY = "LevelPixel/VLM"
def load_clip_checkpoint(self, clip_name):
clip_path = folder_paths.get_full_path("LLavacheckpoints", clip_name)
clip = Llava16ChatHandler(clip_model_path = clip_path, verbose=False)
return (clip, )
class LLavaSamplerSimple:
def __init__(self):
pass
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"image": ("IMAGE",),
"model": ("CUSTOM", {"default": ""}),
"temperature": ("FLOAT", {"default": 0.1, "min": 0.01, "max": 1.0, "step": 0.01}),
"prompt": ("STRING",{"multiline": True} ),
}
}
RETURN_TYPES = ("STRING",)
FUNCTION = "generate_text_simple"
CATEGORY = "LevelPixel/VLM"
def generate_text_simple(self, image, prompt, model, temperature):
pil_image = ToPILImage()(image[0].permute(2, 0, 1))
buffer = BytesIO()
pil_image.save(buffer, format="PNG")
image_bytes = buffer.getvalue()
base64_string = f"data:image/jpeg;base64,{base64.b64encode(image_bytes).decode('utf-8')}"
llm = model
response = llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are an assistant who perfectly describes images."},
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url" : base64_string}},
{"type" : "text", "text": f"{prompt}"}
]
}
],
temperature = temperature,
)
return (f"{response['choices'][0]['message']['content']}", )
class LLavaSamplerAdvanced:
def __init__(self):
pass
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"image": ("IMAGE",),
"model": ("CUSTOM", {"default": ""}),
"max_tokens": ("INT", {"default": 512, "min": 1, "max": 2048, "step": 1}),
"temperature": ("FLOAT", {"default": 0.1, "min": 0.01, "max": 1.0, "step": 0.01}),
"top_p": ("FLOAT", {"default": 0.95, "min": 0.1, "max": 1.0, "step": 0.01}),
"top_k": ("INT", {"default": 40, "step": 1}),
"frequency_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"presence_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"repeat_penalty": ("FLOAT", {"default": 1.1, "step": 0.01}),
"seed": ("INT", {"default": 42, "step":1}),
"prompt": ("STRING",{"multiline": True, "default": ""}),
"system_msg": ("STRING",{"multiline": True, "default" : "You are an assistant who perfectly describes images."}),
}
}
RETURN_TYPES = ("STRING",)
FUNCTION = "generate_text_advanced"
CATEGORY = "LevelPixel/VLM"
def generate_text_advanced(self, image, system_msg, prompt, model, max_tokens, temperature, top_p,
frequency_penalty, presence_penalty, repeat_penalty, top_k,seed):
pil_image = ToPILImage()(image[0].permute(2, 0, 1))
buffer = BytesIO()
pil_image.save(buffer, format="PNG")
image_bytes = buffer.getvalue()
base64_string = f"data:image/jpeg;base64,{base64.b64encode(image_bytes).decode('utf-8')}"
llm = model
response = llm.create_chat_completion(
messages = [
{"role": "system", "content": system_msg},
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url" : base64_string}},
{"type" : "text", "text": f"{prompt}"}
]
}
],
max_tokens = max_tokens,
temperature = temperature,
top_p = top_p,
top_k = top_k,
frequency_penalty = frequency_penalty,
presence_penalty = presence_penalty,
repeat_penalty = repeat_penalty,
seed=seed
)
return (f"{response['choices'][0]['message']['content']}", )
class LLavaSimple:
def __init__(self):
self.llm = None
self.clip = None
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"image": ("IMAGE",),
"ckpt_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
"clip_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
"max_ctx": ("INT", {"default": 4096, "min": 128, "max": 128000, "step": 64}),
"gpu_layers": ("INT", {"default": 27, "min": 0, "max": 100, "step": 1}),
"n_threads": ("INT", {"default": 8, "min": 1, "max": 100, "step": 1}),
"temperature": ("FLOAT", {"default": 0.1, "min": 0.01, "max": 1.0, "step": 0.01}),
"unload": ("BOOLEAN", {"default": False}),
"prompt": ("STRING", {"multiline": True, "forceInput": True}),
}
}
RETURN_TYPES = ("STRING",)
FUNCTION = "generate_text_full_simple"
CATEGORY = "LevelPixel/VLM"
def generate_text_full_simple(self, ckpt_name, clip_name, max_ctx, gpu_layers, n_threads, image, prompt, temperature, unload):
clip_path = folder_paths.get_full_path("LLavacheckpoints", clip_name)
self.clip = Llava16ChatHandler(clip_model_path=clip_path, verbose=False)
ckpt_path = folder_paths.get_full_path("LLavacheckpoints", ckpt_name)
self.llm = Llama(model_path = ckpt_path, chat_handler=self.clip, offload_kqv=True, f16_kv=True,
use_mlock=False, embedding=False, n_batch=1024, last_n_tokens_size=1024,
verbose=True, seed=42, n_ctx = max_ctx, n_gpu_layers=gpu_layers, n_threads=n_threads,
logits_all=True, echo=False)
pil_image = ToPILImage()(image[0].permute(2, 0, 1))
buffer = BytesIO()
pil_image.save(buffer, format="PNG")
image_bytes = buffer.getvalue()
base64_string = f"data:image/jpeg;base64,{base64.b64encode(image_bytes).decode('utf-8')}"
response = self.llm.create_chat_completion(
messages=[
{"role": "system", "content": "You are an assistant who perfectly describes images."},
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": base64_string}},
{"type": "text", "text": f"{prompt}"}
]
}
],
temperature=temperature,
)
if unload and self.llm is not None:
self.llm.close()
del self.llm
self.llm = None
gc.collect()
torch.cuda.empty_cache()
if unload and self.clip is not None:
self.clip._exit_stack.close() # info https://github.com/abetlen/llama-cpp-python/issues/1746
del self.clip
self.clip = None
gc.collect()
torch.cuda.empty_cache()
return (f"{response['choices'][0]['message']['content']}", )
class LLavaAdvanced:
def __init__(self):
self.llm = None
self.clip = None
@classmethod
def INPUT_TYPES(cls):
return {
"required": {
"image": ("IMAGE",),
"ckpt_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
"clip_name": (folder_paths.get_filename_list("LLavacheckpoints"), ),
"max_ctx": ("INT", {"default": 4096, "min": 128, "max": 128000, "step": 64}),
"gpu_layers": ("INT", {"default": 27, "min": 0, "max": 100, "step": 1}),
"n_threads": ("INT", {"default": 8, "min": 1, "max": 100, "step": 1}),
"max_tokens": ("INT", {"default": 512, "min": 1, "max": 2048, "step": 1}),
"temperature": ("FLOAT", {"default": 0.1, "min": 0.01, "max": 1.0, "step": 0.01}),
"top_p": ("FLOAT", {"default": 0.95, "min": 0.1, "max": 1.0, "step": 0.01}),
"top_k": ("INT", {"default": 40, "step": 1}),
"frequency_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"presence_penalty": ("FLOAT", {"default": 0.0, "step": 0.01}),
"repeat_penalty": ("FLOAT", {"default": 1.1, "step": 0.01}),
"seed": ("INT", {"default": 42, "step": 1}),
"unload": ("BOOLEAN", {"default": False}),
"prompt": ("STRING", {"multiline": True, "default": ""}),
"system_msg": ("STRING", {"multiline": True, "default": "You are an assistant who perfectly describes images."}),
}
}
RETURN_TYPES = ("STRING",)
FUNCTION = "generate_text_full_advanced"
CATEGORY = "LevelPixel/VLM"
def generate_text_full_advanced(self, ckpt_name, clip_name, max_ctx, gpu_layers, n_threads, image,
system_msg, prompt, max_tokens, temperature, top_p, top_k, frequency_penalty,
presence_penalty, repeat_penalty, seed, unload):
clip_path = folder_paths.get_full_path("LLavacheckpoints", clip_name)
self.clip = Llava16ChatHandler(clip_model_path=clip_path, verbose=False)
ckpt_path = folder_paths.get_full_path("LLavacheckpoints", ckpt_name)
self.llm = Llama(model_path = ckpt_path, chat_handler=self.clip, offload_kqv=True, f16_kv=True,
use_mlock=False, embedding=False, n_batch=1024, last_n_tokens_size=1024,
verbose=True, seed=42, n_ctx = max_ctx, n_gpu_layers=gpu_layers, n_threads=n_threads,
logits_all=True, echo=False)
pil_image = ToPILImage()(image[0].permute(2, 0, 1))
buffer = BytesIO()
pil_image.save(buffer, format="PNG")
image_bytes = buffer.getvalue()
base64_string = f"data:image/jpeg;base64,{base64.b64encode(image_bytes).decode('utf-8')}"
response = self.llm.create_chat_completion(
messages=[
{"role": "system", "content": system_msg},
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": base64_string}},
{"type": "text", "text": f"{prompt}"}
]
}
],
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
top_k=top_k,
frequency_penalty=frequency_penalty,
presence_penalty=presence_penalty,
repeat_penalty=repeat_penalty,
seed=seed,
)
if unload and self.llm is not None:
self.llm.close()
del self.llm
self.llm = None
gc.collect()
torch.cuda.empty_cache()
if unload and self.clip is not None:
self.clip._exit_stack.close() # info https://github.com/abetlen/llama-cpp-python/issues/1746
del self.clip
self.clip = None
gc.collect()
torch.cuda.empty_cache()
return (f"{response['choices'][0]['message']['content']}", )
NODE_CLASS_MAPPINGS = {
"LLavaLoader|LP": LLavaLoader,
"LLavaClipLoader|LP": LLavaClipLoader,
"LLavaSamplerSimple|LP": LLavaSamplerSimple,
"LLavaSamplerAdvanced|LP": LLavaSamplerAdvanced,
"LLavaSimple|LP": LLavaSimple,
"LLavaAdvanced|LP": LLavaAdvanced,
}
NODE_DISPLAY_NAME_MAPPINGS = {
"LLavaLoader|LP": "LLava Loader [LP]",
"LLavaClipLoader|LP": "LLava Clip Loader [LP]",
"LLavaSamplerSimple|LP": "LLava Sampler Simple [LP]",
"LLavaSamplerAdvanced|LP": "LLava Sampler Advanced [LP]",
"LLavaSimple|LP": "LLava Simple [LP]",
"LLavaAdvanced|LP": "LLava Advanced [LP]",
}
pyproject.toml
+14
View File
@@ -0,0 +1,14 @@
[project]
name = "comfyui-level-pixel-advanced"
description = "Various advanced nodes of the Level Pixel company. Includes convenient advanced nodes for working with LLM и VLM models."
version = "1.2.0"
license = { file = "LICENSE" }
dependencies = ["torch>=2.0.1", "torchvision>=0.15.2", "transformers>=4.46", "pillow>=9.4.0", "numpy>=1.26.4", "matplotlib"]
[project.urls]
Repository = "https://github.com/LevelPixel/ComfyUI-LevelPixel-Advanced"
[tool.comfy]
PublisherId = "Level Pixel"
DisplayName = "ComfyUI Level Pixel Advanced"
Icon = ""
requirements.txt
+5
View File
@@ -0,0 +1,5 @@
torch>=2.0.1
torchvision>=0.15.2
pillow>=9.4.0
numpy>=1.26.4
matplotlib