slahiriandClaude Opus 4.5
7f1186d412
New Features: - SID_PromptCompose node with Standard and Enhance with AI modes - SID_PromptSynthesis node for VLM-based prompt generation - SID_ImageAnalysis node for comprehensive image analysis - Text LLM support (Qwen2.5 0.5B-7B) for prompt enhancement - PixAI tagger integration Documentation: - docs/image_tokenization_spec.md - Full technical specification for tokenization → classification → assembly pipeline - docs/implementation_plan.md - 8-phase implementation roadmap - docs/SID_PromptCompose.md - Node usage documentation Infrastructure: - core/compose/ module with base, pipeline, standard, llm generators - core/log.py centralized logging - Config files for Qwen2.5 text models (YAML) - Web assets for ComfyUI integration This commit establishes the foundation for rewriting the compose pipeline based on the tokenization specification. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
148 lines
4.2 KiB
Python
148 lines
4.2 KiB
Python
# -*- coding: utf-8 -*-
|
|
"""
|
|
SID Photography Toolkit v5.0
|
|
|
|
AI-powered image captioning for ComfyUI.
|
|
Clean, modular architecture with plug-and-play models.
|
|
|
|
Author: Siddhartha Lahiri
|
|
License: MIT
|
|
"""
|
|
|
|
__version__ = "5.0.0"
|
|
|
|
# Import nodes
|
|
from .nodes import (
|
|
SID_ZImagePromptGenerator,
|
|
SID_TaggerConfig,
|
|
SID_ImageAnalysis,
|
|
SID_PromptSynthesis,
|
|
)
|
|
from .nodes.prompt_compose import SID_PromptCompose
|
|
|
|
# V1 API registration
|
|
NODE_CLASS_MAPPINGS = {
|
|
"SID_ZImagePromptGenerator": SID_ZImagePromptGenerator,
|
|
"SID_TaggerConfig": SID_TaggerConfig,
|
|
"SID_ImageAnalysis": SID_ImageAnalysis,
|
|
"SID_PromptSynthesis": SID_PromptSynthesis,
|
|
"SID_PromptCompose": SID_PromptCompose,
|
|
}
|
|
|
|
NODE_DISPLAY_NAME_MAPPINGS = {
|
|
"SID_ZImagePromptGenerator": "SID Z-Image Prompt Generator",
|
|
"SID_TaggerConfig": "SID Tagger Config",
|
|
"SID_ImageAnalysis": "SID Image Analysis",
|
|
"SID_PromptSynthesis": "SID Prompt Synthesis",
|
|
"SID_PromptCompose": "SID Prompt Compose",
|
|
}
|
|
|
|
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
|
|
|
|
# Auto-install dependencies
|
|
def _install_dependencies():
|
|
"""Auto-install required dependencies at startup."""
|
|
import subprocess
|
|
import sys
|
|
|
|
# Required packages: (import_name, pip_package)
|
|
required = [
|
|
("yaml", "pyyaml"),
|
|
("onnxruntime", "onnxruntime-gpu"),
|
|
("cv2", "opencv-python"),
|
|
("timm", "timm"),
|
|
("huggingface_hub", "huggingface_hub"),
|
|
]
|
|
|
|
# Optional packages
|
|
optional = [
|
|
("nudenet", "nudenet"),
|
|
("pyiqa", "pyiqa"),
|
|
("ultralytics", "ultralytics"),
|
|
("imgutils", "dghs-imgutils>=0.19.0"),
|
|
]
|
|
|
|
def is_installed(module_name):
|
|
try:
|
|
__import__(module_name)
|
|
return True
|
|
except ImportError:
|
|
return False
|
|
|
|
def install(package, quiet=True):
|
|
print(f"[AI-Photo-Toolkit] Installing {package}...")
|
|
try:
|
|
cmd = [sys.executable, "-m", "pip", "install", package]
|
|
if quiet:
|
|
cmd.append("-q")
|
|
subprocess.check_call(cmd, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
|
|
else:
|
|
# Show output for debugging
|
|
subprocess.check_call(cmd)
|
|
return True
|
|
except subprocess.CalledProcessError as e:
|
|
# Try without GPU for onnxruntime
|
|
if package == "onnxruntime-gpu":
|
|
print(f"[AI-Photo-Toolkit] GPU version failed, trying CPU...")
|
|
try:
|
|
subprocess.check_call(
|
|
[sys.executable, "-m", "pip", "install", "onnxruntime", "-q"],
|
|
stdout=subprocess.DEVNULL,
|
|
stderr=subprocess.DEVNULL,
|
|
)
|
|
return True
|
|
except subprocess.CalledProcessError:
|
|
pass
|
|
print(f"[AI-Photo-Toolkit] Failed to install {package}: {e}")
|
|
return False
|
|
except Exception as e:
|
|
print(f"[AI-Photo-Toolkit] Error installing {package}: {e}")
|
|
return False
|
|
|
|
# Install required
|
|
for module, package in required:
|
|
if not is_installed(module):
|
|
install(package)
|
|
|
|
# Install optional (show output for debugging)
|
|
for module, package in optional:
|
|
if not is_installed(module):
|
|
install(package, quiet=False)
|
|
|
|
|
|
# Startup
|
|
def _print_startup():
|
|
print(f"\n[AI-Photo-Toolkit] v{__version__} loading...")
|
|
|
|
# Auto-install missing deps
|
|
_install_dependencies()
|
|
|
|
# Check what's available now
|
|
available = []
|
|
missing = []
|
|
|
|
checks = [
|
|
("onnxruntime", "WD14, JoyTag"),
|
|
("cv2", "Photography, Composition"),
|
|
("timm", "Fashion"),
|
|
("nudenet", "NudeNet"),
|
|
("pyiqa", "IQA"),
|
|
("ultralytics", "YOLOv8"),
|
|
("imgutils", "PixAI"),
|
|
]
|
|
|
|
for module, taggers in checks:
|
|
try:
|
|
__import__(module)
|
|
available.append(taggers)
|
|
except ImportError:
|
|
missing.append(taggers)
|
|
|
|
print(f"[AI-Photo-Toolkit] v{__version__} ready!")
|
|
print(f"[AI-Photo-Toolkit] Available: {', '.join(available)}")
|
|
if missing:
|
|
print(f"[AI-Photo-Toolkit] Unavailable: {', '.join(missing)}")
|
|
print()
|
|
|
|
_print_startup()
|