gaia sd "create a cute robot kitten and tell me a short story about it"

🤖 Processing: 'create a cute robot kitten and tell me a short story about it'

📝 Step 1: Generating image...
🎨 Enhanced: "adorable robotic kitten, glowing LED eyes, soft lighting..."
⠋ Generating (4 steps)... (17s)

[IMAGE PREVIEW]

📝 Step 2: Analyzing with VLM...
👁️ "A captivating robotic kitten with chrome body, amber eyes..."

📝 Step 3: Creating story...
📖 Story: "In Cyber-Cat City, Whiskers the robot kitten..."

✅ Complete! Image + Story created in 35 seconds

Open image? [Y/n]:

# Just an image (no story)
gaia sd "robot kitten"

# Image with story (automatic)
gaia sd "create a cute robot kitten and tell me a short story about it"

# Multiple images
gaia sd "create 3 robot kittens"

# Analyze existing image
gaia sd "tell me about .gaia/cache/sd/images/robot.png"

from gaia.agents.base import Agent
from gaia.sd import SDToolsMixin
from gaia.vlm import VLMToolsMixin

class SDAgent(Agent, SDToolsMixin, VLMToolsMixin):
    def __init__(self, config):
        # Initialize Agent base with LLM config
        super().__init__(
            model_id=config.model_id,  # Qwen3-8B for agentic reasoning
            max_steps=config.max_steps,
            min_context_size=16384,  # 16K for multi-step planning
        )

        # Initialize SD tools (auto-registers generate_image, list_sd_models, etc.)
        self.init_sd(
            output_dir=config.output_dir,
            default_model=config.sd_model,  # SDXL-Turbo
        )

        # Initialize VLM tools (auto-registers analyze_image, create_story_from_image, etc.)
        self.init_vlm(model="Qwen3-VL-4B-Instruct-GGUF")

# In SDAgent._register_tools()
@tool(
    atomic=True,  # Single-step execution (no multi-step planning)
    name="create_story_from_last_image",
    description="Analyze last SD image and create story",
)
def create_story_from_last_image():
    """SD-specific wrapper - no need to specify image path."""
    last_image = self.sd_generations[-1]["image_path"]

    # Calls generic VLM tool
    return self._create_story_from_image(last_image, story_style="whimsical")

# The @tool decorator automatically registers it - no need to call register_tool()

User: "create a robot kitten and tell me a story"

LLM Planning:
{
  "thought": "Need to generate image first, then create story",
  "plan": [
    {"tool": "generate_image", "tool_args": {"prompt": "enhanced..."}},
    {"tool": "create_story_from_last_image", "tool_args": {}}
  ]
}

# 1. Mixin tools registered during init
@tool(atomic=True, name="generate_image")
def generate_image(prompt, model, size, steps, cfg_scale):
    ...

# 2. Agent-specific tools registered in _register_tools()
@tool(atomic=True, name="create_story_from_last_image")
def create_story_from_last_image():
    ...

# 3. LLM sees all registered tools in system prompt
_TOOL_REGISTRY = {
    "generate_image": {...},
    "analyze_image": {...},
    "create_story_from_image": {...},
    "create_story_from_last_image": {...},  # Custom SD tool
}

self.sd_generations = [
    {
        "image_path": ".gaia/cache/sd/images/robot_kitten_abc123.png",
        "prompt": "enhanced prompt with quality keywords",
        "model": "SDXL-Turbo",
        "size": "512x512",
        "steps": 4,
        "seed": 42,
        "generation_time_s": 17.0,
        "image_hash": "a1b2c3d4...",  # For deduplication
    },
    # ... more generations
]

User Request
    ↓
Qwen3-8B (LLM) - Decides: "Need image + story"
    ↓
Calls: generate_image(enhanced_prompt)
    ↓
SDXL-Turbo - Generates image → Returns image_path
    ↓
Qwen3-8B (LLM) - Decides: "Now create story"
    ↓
Calls: create_story_from_last_image()
    ↓
Qwen3-VL-4B (VLM) - Analyzes image → Creates story
    ↓
Qwen3-8B (LLM) - Formats final response
    ↓
User receives: Enhanced prompt + Image + Story

# Mixin provides static base + instance-specific prompts
class SDToolsMixin:
    @staticmethod
    def get_base_sd_guidelines() -> str:
        """Research-backed SD prompt engineering (static)."""
        return BASE_GUIDELINES + WORKFLOW_INSTRUCTIONS

    def get_sd_system_prompt(self) -> str:
        """Base + model-specific enhancements."""
        base = self.get_base_sd_guidelines()
        if hasattr(self, 'sd_default_model'):
            # Add model-specific parts (SDXL-Turbo vs SDXL-Base, etc.)
            return base + MODEL_SPECIFIC_PROMPTS[self.sd_default_model]
        return base

# Print final system prompt
python -c "from gaia.agents.sd import SDAgent; agent = SDAgent(); print(agent.system_prompt)"

# View just SD guidelines
python -c "from gaia.sd import SDToolsMixin; print(SDToolsMixin.get_base_sd_guidelines())"

gaia sd "robot kitten"  # Different image each time

gaia sd "robot kitten" --seed 42  # Same image every time with seed 42