slahiriandClaude
788798df95
FIXES: 1. Color Style Not Applied (CRITICAL BUG FIX) - Completely rewrote color style enforcement mechanism - Added explicit comma-separated term mappings for each color style - Implemented ⚠️ CRITICAL warnings with MANDATORY requirements - Added contradictory term exclusions (B&W forbids "color", Color forbids "monochrome") - Color terms now MUST appear first in prompt sequence - Example: "Black and White" → "black and white photography, monochrome, grayscale, B&W, no color" 2. Model Input Connection Support - Added force_input=False to target_model parameter - Can now connect model name from model loader nodes - Maintains ability to type model name manually - Updated tooltip to clarify dual functionality 3. Enhanced Model Detection Patterns - SDXL: +9 patterns (pony, animagine, realvis xl, zavychroma, duchaiten, dreamshaper xl, crystal clear, hellonijicute, counterfeit xl) - SD 1.5: +7 patterns (deliberate, epicrealism, cyberrealistic, majicmix, chilloutmix, revanimated, absolutereality, analog madness, perfect world) - More comprehensive automatic model type detection CLARIFICATIONS: - Model Research Methodology * Updated docstring to clarify using pattern matching (not live web search) * Added note about future CivitAI/HuggingFace API integration * Changed research_source from "inference" to "pattern_matching" * Explained that real-time API calls require external dependencies Technical Details: - Color style system now provides exact comma-separated terms to use - Enforcement changed from "include as PRIMARY term" to "Start with EXACT terms: X, Y, Z" - Added explicit prohibition against contradictory terms - Model detection now covers 30+ popular model names across all types Why These Fixes: User reported color style (B&W) not being applied even when selected. Root cause was insufficient enforcement in system prompt. New approach uses explicit term lists and critical warnings to Claude, ensuring compliance. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
91 lines
2.7 KiB
Python
91 lines
2.7 KiB
Python
"""
|
|
ComfyUI-AI-Photography-Toolkit
|
|
A collection of AI-powered photography and image generation tools for ComfyUI.
|
|
All nodes are prefixed with SID_ for easy identification.
|
|
|
|
Author: Siddhartha Lahiri
|
|
Version: 3.0.1
|
|
"""
|
|
|
|
__version__ = "3.0.1"
|
|
|
|
import os
|
|
import sys
|
|
import subprocess
|
|
import importlib.util
|
|
|
|
# Auto-install dependencies
|
|
def install_dependencies():
|
|
"""
|
|
Automatically install required dependencies if not already installed.
|
|
"""
|
|
dependencies = {
|
|
"anthropic": "anthropic>=0.39.0",
|
|
}
|
|
|
|
python_exe = sys.executable
|
|
|
|
for package_name, package_spec in dependencies.items():
|
|
# Check if package is already installed
|
|
if importlib.util.find_spec(package_name) is None:
|
|
print(f"\n{'='*60}")
|
|
print(f"Installing {package_name} for SID Photography Toolkit...")
|
|
print(f"{'='*60}")
|
|
try:
|
|
subprocess.check_call(
|
|
[python_exe, "-m", "pip", "install", package_spec],
|
|
stdout=subprocess.PIPE,
|
|
stderr=subprocess.PIPE
|
|
)
|
|
print(f"{package_name} installed successfully!")
|
|
except subprocess.CalledProcessError as e:
|
|
print(f"ERROR: Failed to install {package_name}")
|
|
print(f"Please manually install: pip install {package_spec}")
|
|
print(f"Error: {e}")
|
|
print(f"{'='*60}\n")
|
|
|
|
# Install dependencies on module load
|
|
install_dependencies()
|
|
|
|
from typing_extensions import override
|
|
from comfy_api.latest import ComfyExtension, io
|
|
|
|
# Import all node classes
|
|
from .sid_ai_prompt_generator import SID_AIPromptGenerator
|
|
|
|
|
|
class SIDPhotographyToolkitExtension(ComfyExtension):
|
|
"""
|
|
Extension class for SID Photography Toolkit.
|
|
Registers all SID_ prefixed nodes with ComfyUI.
|
|
"""
|
|
|
|
@override
|
|
async def get_node_list(self) -> list[type[io.ComfyNode]]:
|
|
"""
|
|
Return list of all nodes in this extension.
|
|
Add new nodes here as they are created.
|
|
"""
|
|
return [
|
|
SID_AIPromptGenerator,
|
|
# Future nodes will be added here
|
|
# SID_ImageAnalyzer,
|
|
# SID_StyleTransfer,
|
|
# etc.
|
|
]
|
|
|
|
|
|
async def comfy_entrypoint() -> SIDPhotographyToolkitExtension:
|
|
"""
|
|
ComfyUI calls this function to load the extension and its nodes.
|
|
This is the entry point for the custom node package.
|
|
"""
|
|
print("\n" + "="*60)
|
|
print(f"Loading SID Photography Toolkit v{__version__} for ComfyUI")
|
|
print("="*60)
|
|
print("Nodes loaded:")
|
|
print(" - SID_AIPromptGenerator: AI-powered prompt generation from images")
|
|
print("="*60 + "\n")
|
|
|
|
return SIDPhotographyToolkitExtension()
|