slahiriandClaude Opus 4.5
5086598eb8
## New Features - Add web-based Prompt Editor at /sid/prompt-editor - Monaco editor with TOML syntax highlighting - File browser for prompt templates - Save with TOML validation and auto-backup - Reset to git default functionality - Add prompt_generator_core.py for standalone batch processing - Add sid_prompt_generator_v2.py with simplified interface - Add sid_prompt_debug.py for prompt quality evaluation - Add cv_analyzer.py for YOLO-based human detection ## Prompt Template Improvements - Restructure prompts into separate TOML files (portrait, scene, classification) - Add sentence-by-sentence structure for local models - Add comprehensive hair texture vocabulary (straight/wavy/curly/bangs) - Add makeup vocabulary (smoky eyes, lipstick colors) - Improve basic tier prompts to output sentences instead of keyword lists ## API Call Optimization - Standard mode: Single API call (ignores reasoning) - Detailed + reasoning OFF: Single API call with detailed prompts - Detailed + reasoning ON: Multi-step agentic analysis ## Dependencies - Add aiohttp for web routes - Add tomlkit for TOML editing with comment preservation 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
388 lines
9.8 KiB
JSON
388 lines
9.8 KiB
JSON
{
|
|
"version": "1.0.0",
|
|
"last_updated": "2025-12-14T00:00:00Z",
|
|
"description": "Model-specific tips for vision LLMs used in prompt generation",
|
|
|
|
"vision_models": {
|
|
"Qwen2.5-VL-7B-Instruct": {
|
|
"provider": "local",
|
|
"parameter_count": "7B",
|
|
"description": "Alibaba's Qwen2.5 Vision-Language model",
|
|
"strengths": [
|
|
"Human detection and pose analysis",
|
|
"Color accuracy",
|
|
"Scene composition understanding",
|
|
"Good instruction following",
|
|
"Efficient at 7B size"
|
|
],
|
|
"weaknesses": [
|
|
"Small accessories may be missed",
|
|
"Fine patterns can be overlooked",
|
|
"Fabric textures sometimes vague",
|
|
"May miss jewelry details"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.2,
|
|
"quantization": "8-bit",
|
|
"repetition_penalty": 1.2,
|
|
"top_p": 0.9
|
|
},
|
|
"prompt_tips": [
|
|
"Explicitly ask for accessory details",
|
|
"Request fabric material description",
|
|
"Ask for pattern details separately if needed",
|
|
"Use structured output requests"
|
|
],
|
|
"known_issues": [
|
|
"At 4-bit quantization, detail detection reduces",
|
|
"May generate verbose output without length guidance"
|
|
]
|
|
},
|
|
|
|
"Qwen2-VL-72B-Instruct": {
|
|
"provider": "local",
|
|
"parameter_count": "72B",
|
|
"description": "Large Qwen2 Vision-Language model",
|
|
"strengths": [
|
|
"Excellent detail recognition",
|
|
"Strong reasoning capabilities",
|
|
"Better accessory detection than 7B",
|
|
"Good at complex scenes"
|
|
],
|
|
"weaknesses": [
|
|
"High VRAM requirement",
|
|
"Slower inference"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3,
|
|
"quantization": "4-bit",
|
|
"repetition_penalty": 1.1
|
|
},
|
|
"prompt_tips": [
|
|
"Can handle complex multi-part requests",
|
|
"Good for detailed analysis",
|
|
"Responds well to structured prompts"
|
|
]
|
|
},
|
|
|
|
"LLaVA-1.6-34B": {
|
|
"provider": "local",
|
|
"parameter_count": "34B",
|
|
"description": "Large Language and Vision Assistant",
|
|
"strengths": [
|
|
"Detailed descriptions",
|
|
"Scene understanding",
|
|
"Good conversation ability",
|
|
"Strong at complex queries"
|
|
],
|
|
"weaknesses": [
|
|
"Can be verbose",
|
|
"Occasional hallucination",
|
|
"High VRAM usage"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3,
|
|
"repetition_penalty": 1.3,
|
|
"max_tokens": 1024
|
|
},
|
|
"prompt_tips": [
|
|
"Use structured output requests",
|
|
"Set clear length limits",
|
|
"Be specific about what to include/exclude",
|
|
"Request bullet points for structured output"
|
|
],
|
|
"known_issues": [
|
|
"May add narrative commentary",
|
|
"Can repeat information"
|
|
]
|
|
},
|
|
|
|
"LLaVA-1.5-7B": {
|
|
"provider": "local",
|
|
"parameter_count": "7B",
|
|
"description": "Efficient LLaVA variant",
|
|
"strengths": [
|
|
"Fast inference",
|
|
"Low VRAM usage",
|
|
"Good general understanding"
|
|
],
|
|
"weaknesses": [
|
|
"Less detailed than larger models",
|
|
"May miss subtle elements"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3,
|
|
"repetition_penalty": 1.2
|
|
},
|
|
"prompt_tips": [
|
|
"Keep requests focused",
|
|
"Ask about specific elements",
|
|
"Good for quick analysis"
|
|
]
|
|
},
|
|
|
|
"Florence-2-large": {
|
|
"provider": "local",
|
|
"parameter_count": "0.7B",
|
|
"description": "Microsoft's Florence-2 vision model",
|
|
"strengths": [
|
|
"Very fast",
|
|
"Low VRAM",
|
|
"Good at detection tasks",
|
|
"Structured output"
|
|
],
|
|
"weaknesses": [
|
|
"Limited descriptive ability",
|
|
"Best for specific tasks",
|
|
"Less conversational"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.2
|
|
},
|
|
"prompt_tips": [
|
|
"Use task-specific prompts",
|
|
"Good for object detection",
|
|
"Combine with other models for full descriptions"
|
|
]
|
|
},
|
|
|
|
"Moondream2": {
|
|
"provider": "local",
|
|
"parameter_count": "1.6B",
|
|
"description": "Compact vision-language model",
|
|
"strengths": [
|
|
"Extremely efficient",
|
|
"Fast inference",
|
|
"Can run on CPU"
|
|
],
|
|
"weaknesses": [
|
|
"Limited detail",
|
|
"Basic descriptions",
|
|
"May miss nuances"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3
|
|
},
|
|
"prompt_tips": [
|
|
"Keep questions simple",
|
|
"Good for basic image understanding",
|
|
"Use for quick checks"
|
|
]
|
|
},
|
|
|
|
"InternVL2-8B": {
|
|
"provider": "local",
|
|
"parameter_count": "8B",
|
|
"description": "OpenGVLab's InternVL2 model",
|
|
"strengths": [
|
|
"Good balance of size/quality",
|
|
"Strong OCR ability",
|
|
"Multi-image support"
|
|
],
|
|
"weaknesses": [
|
|
"May be verbose"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3,
|
|
"repetition_penalty": 1.2
|
|
},
|
|
"prompt_tips": [
|
|
"Good for text in images",
|
|
"Can compare multiple images"
|
|
]
|
|
},
|
|
|
|
"Phi-3.5-Vision": {
|
|
"provider": "local",
|
|
"parameter_count": "4.2B",
|
|
"description": "Microsoft Phi-3.5 with vision",
|
|
"strengths": [
|
|
"Efficient size",
|
|
"Good reasoning",
|
|
"Fast inference"
|
|
],
|
|
"weaknesses": [
|
|
"Less detailed than larger models"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3
|
|
},
|
|
"prompt_tips": [
|
|
"Good for reasoning tasks",
|
|
"Efficient for multiple queries"
|
|
]
|
|
},
|
|
|
|
"claude-sonnet-4-5-20250929": {
|
|
"provider": "anthropic",
|
|
"parameter_count": "unknown",
|
|
"description": "Anthropic Claude Sonnet 4.5",
|
|
"strengths": [
|
|
"Excellent accuracy",
|
|
"Strong instruction following",
|
|
"Good structured output",
|
|
"Reliable and consistent",
|
|
"Handles complex prompts"
|
|
],
|
|
"weaknesses": [
|
|
"API cost",
|
|
"May be conservative in descriptions"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3
|
|
},
|
|
"prompt_tips": [
|
|
"Can handle complex multi-part prompts",
|
|
"Excellent with JSON output",
|
|
"Good at following specific formats",
|
|
"Reliable for production use"
|
|
]
|
|
},
|
|
|
|
"claude-opus-4-5-20251101": {
|
|
"provider": "anthropic",
|
|
"parameter_count": "unknown",
|
|
"description": "Anthropic Claude Opus 4.5 (most capable)",
|
|
"strengths": [
|
|
"Highest accuracy",
|
|
"Best reasoning",
|
|
"Excellent detail detection",
|
|
"Strong at nuanced descriptions"
|
|
],
|
|
"weaknesses": [
|
|
"Higher API cost",
|
|
"Slower than Sonnet"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3
|
|
},
|
|
"prompt_tips": [
|
|
"Best for evaluation and analysis",
|
|
"Excellent for complex tasks",
|
|
"Use for quality-critical applications"
|
|
]
|
|
},
|
|
|
|
"gpt-4o": {
|
|
"provider": "openai",
|
|
"parameter_count": "unknown",
|
|
"description": "OpenAI GPT-4o multimodal",
|
|
"strengths": [
|
|
"Strong general ability",
|
|
"Good at creative descriptions",
|
|
"Handles ambiguity well"
|
|
],
|
|
"weaknesses": [
|
|
"API cost",
|
|
"May add interpretation"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3
|
|
},
|
|
"prompt_tips": [
|
|
"Clear instructions help",
|
|
"Good at following examples",
|
|
"Can be creative"
|
|
]
|
|
},
|
|
|
|
"gemini-2.0-flash": {
|
|
"provider": "google",
|
|
"parameter_count": "unknown",
|
|
"description": "Google Gemini 2.0 Flash",
|
|
"strengths": [
|
|
"Fast inference",
|
|
"Good multimodal ability",
|
|
"Competitive pricing"
|
|
],
|
|
"weaknesses": [
|
|
"May be less detailed"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3
|
|
},
|
|
"prompt_tips": [
|
|
"Good for quick analysis",
|
|
"Handles multiple images"
|
|
]
|
|
},
|
|
|
|
"llava:latest": {
|
|
"provider": "ollama",
|
|
"parameter_count": "7B",
|
|
"description": "Ollama LLaVA model",
|
|
"strengths": [
|
|
"Easy local deployment",
|
|
"No API costs",
|
|
"Good general ability"
|
|
],
|
|
"weaknesses": [
|
|
"Depends on Ollama setup",
|
|
"May vary by version"
|
|
],
|
|
"optimal_settings": {
|
|
"temperature": 0.3
|
|
},
|
|
"prompt_tips": [
|
|
"Good for local development",
|
|
"Test with your specific version"
|
|
]
|
|
}
|
|
},
|
|
|
|
"provider_comparison": {
|
|
"accuracy": {
|
|
"ranking": [
|
|
"claude-opus-4-5-20251101",
|
|
"claude-sonnet-4-5-20250929",
|
|
"gpt-4o",
|
|
"Qwen2-VL-72B-Instruct",
|
|
"LLaVA-1.6-34B",
|
|
"Qwen2.5-VL-7B-Instruct",
|
|
"InternVL2-8B"
|
|
]
|
|
},
|
|
"speed": {
|
|
"ranking": [
|
|
"Florence-2-large",
|
|
"Moondream2",
|
|
"Phi-3.5-Vision",
|
|
"gemini-2.0-flash",
|
|
"Qwen2.5-VL-7B-Instruct",
|
|
"LLaVA-1.5-7B"
|
|
]
|
|
},
|
|
"cost_effectiveness": {
|
|
"ranking": [
|
|
"Local models (free)",
|
|
"gemini-2.0-flash",
|
|
"gpt-4o-mini",
|
|
"claude-sonnet-4-5-20250929",
|
|
"gpt-4o",
|
|
"claude-opus-4-5-20251101"
|
|
]
|
|
}
|
|
},
|
|
|
|
"quantization_effects": {
|
|
"4-bit": {
|
|
"vram_reduction": "~75%",
|
|
"quality_impact": "Noticeable on fine details",
|
|
"speed_impact": "Faster due to memory efficiency",
|
|
"recommended_for": "Limited VRAM, quick iterations"
|
|
},
|
|
"8-bit": {
|
|
"vram_reduction": "~50%",
|
|
"quality_impact": "Minimal quality loss",
|
|
"speed_impact": "Slightly faster than FP16",
|
|
"recommended_for": "Best balance of quality/efficiency"
|
|
},
|
|
"fp16": {
|
|
"vram_reduction": "0%",
|
|
"quality_impact": "Full model quality",
|
|
"speed_impact": "Baseline",
|
|
"recommended_for": "Quality-critical applications"
|
|
}
|
|
}
|
|
}
|