Class swarmauri_standard.image_gens.BlackForestImgGenModel.BlackForestImgGenModel

swarmauri_standard.image_gens.BlackForestImgGenModel.BlackForestImgGenModel

BlackForestImgGenModel(**kwargs)

Bases: ImageGenBase

A model for generating images using FluxPro's image generation models through the Black Forest API. Link to API key: https://api.bfl.ml/auth/profile

Initializes the BlackForestImgGenModel instance with HTTP clients. Args: **kwarg (Dict[str, Any]): Additional arguments including api_key and allowed_models.

Source code in swarmauri_standard/image_gens/BlackForestImgGenModel.py

def __init__(self, **kwargs: Dict[str, Any]):
    """
    Initializes the BlackForestImgGenModel instance with HTTP clients.
    Args:
        **kwarg (Dict[str, Any]): Additional arguments including api_key and allowed_models.
    """
    super().__init__(**kwargs)
    self._headers = {
        "Content-Type": "application/json",
        "X-Key": self.api_key.get_secret_value(),
    }
    self._client = httpx.Client(headers=self._headers, timeout=self.timeout)

api_key instance-attribute

api_key

allowed_models class-attribute instance-attribute

allowed_models = ['flux-pro-1.1', 'flux-pro', 'flux-dev']

timeout class-attribute instance-attribute

timeout = 600.0

name class-attribute instance-attribute

name = 'flux-pro-1.1'

type class-attribute instance-attribute

type = 'BlackForestImgGenModel'

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="forbid", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

resource class-attribute instance-attribute

resource = Field(default=IMAGE_GEN.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

generate_image

generate_image(
    prompt,
    width=1024,
    height=768,
    steps=None,
    prompt_upsampling=False,
    seed=None,
    guidance=None,
    safety_tolerance=None,
    interval=None,
    max_wait_time=300,
    check_interval=10,
)

Generates an image based on the prompt and waits for the result synchronously.

PARAMETER	DESCRIPTION
prompt	The text prompt for image generation TYPE: str
width	Image width in pixels TYPE: int DEFAULT: 1024
height	Image height in pixels TYPE: int DEFAULT: 768
steps	Number of inference steps TYPE: Optional[int] DEFAULT: None
prompt_upsampling	Whether to use prompt upsampling TYPE: bool DEFAULT: False
seed	Random seed for generation TYPE: Optional[int] DEFAULT: None
guidance	Guidance scale TYPE: Optional[float] DEFAULT: None
safety_tolerance	Safety tolerance level TYPE: Optional[int] DEFAULT: None
interval	Interval parameter (flux-pro only) TYPE: Optional[float] DEFAULT: None
max_wait_time	Maximum time to wait for result in seconds TYPE: int DEFAULT: 300
check_interval	Time between status checks in seconds TYPE: int DEFAULT: 10

RETURNS	DESCRIPTION
Dict	Dictionary containing the image URL and other result information TYPE: Dict

Source code in swarmauri_standard/image_gens/BlackForestImgGenModel.py

def generate_image(
    self,
    prompt: str,
    width: int = 1024,
    height: int = 768,
    steps: Optional[int] = None,
    prompt_upsampling: bool = False,
    seed: Optional[int] = None,
    guidance: Optional[float] = None,
    safety_tolerance: Optional[int] = None,
    interval: Optional[float] = None,
    max_wait_time: int = 300,
    check_interval: int = 10,
) -> Dict:
    """
    Generates an image based on the prompt and waits for the result synchronously.

    Args:
        prompt (str): The text prompt for image generation
        width (int): Image width in pixels
        height (int): Image height in pixels
        steps (Optional[int]): Number of inference steps
        prompt_upsampling (bool): Whether to use prompt upsampling
        seed (Optional[int]): Random seed for generation
        guidance (Optional[float]): Guidance scale
        safety_tolerance (Optional[int]): Safety tolerance level
        interval (Optional[float]): Interval parameter (flux-pro only)
        max_wait_time (int): Maximum time to wait for result in seconds
        check_interval (int): Time between status checks in seconds

    Returns:
        Dict: Dictionary containing the image URL and other result information
    """
    endpoint = f"v1/{self.name}"
    data = {
        "prompt": prompt,
        "width": width,
        "height": height,
        "prompt_upsampling": prompt_upsampling,
    }

    if steps is not None:
        data["steps"] = steps
    if seed is not None:
        data["seed"] = seed
    if guidance is not None:
        data["guidance"] = guidance
    if safety_tolerance is not None:
        data["safety_tolerance"] = safety_tolerance
    if interval is not None and self.name == "flux-pro":
        data["interval"] = interval

    response = self._send_request(endpoint, data)
    task_id = response["id"]

    start_time = time.time()
    while time.time() - start_time < max_wait_time:
        result = self._get_result(task_id)
        if result["status"] == "Ready":
            return result["result"]["sample"]
        elif result["status"] in [
            "Error",
            "Request Moderated",
            "Content Moderated",
        ]:
            raise Exception(f"Task failed with status: {result['status']}")
        time.sleep(check_interval)

    raise TimeoutError(f"Image generation timed out after {max_wait_time} seconds")

agenerate_image async

agenerate_image(prompt, **kwargs)

Asynchronously generates an image based on the prompt and waits for the result.

PARAMETER	DESCRIPTION
prompt	The text prompt for image generation TYPE: str
**kwargs	Additional arguments passed to generate_image TYPE: Dict[str, Any] DEFAULT: {}

RETURNS	DESCRIPTION
Dict	Dictionary containing the image URL and other result information TYPE: Dict

Source code in swarmauri_standard/image_gens/BlackForestImgGenModel.py

async def agenerate_image(self, prompt: str, **kwargs: Dict[str, Any]) -> Dict:
    """
    Asynchronously generates an image based on the prompt and waits for the result.

    Args:
        prompt (str): The text prompt for image generation
        **kwargs: Additional arguments passed to generate_image

    Returns:
        Dict: Dictionary containing the image URL and other result information
    """
    try:
        endpoint = f"v1/{self.name}"
        data = {
            "prompt": prompt,
            "width": kwargs.get("width", 1024),
            "height": kwargs.get("height", 768),
            "prompt_upsampling": kwargs.get("prompt_upsampling", False),
        }

        optional_params = [
            "steps",
            "seed",
            "guidance",
            "safety_tolerance",
        ]
        for param in optional_params:
            if param in kwargs:
                data[param] = kwargs[param]

        if "interval" in kwargs and self.name == "flux-pro":
            data["interval"] = kwargs["interval"]

        response = await self._async_send_request(endpoint, data)
        task_id = response["id"]

        max_wait_time = kwargs.get("max_wait_time", 300)
        check_interval = kwargs.get("check_interval", 10)
        start_time = time.time()

        while time.time() - start_time < max_wait_time:
            result = await self._async_get_result(task_id)
            if result["status"] == "Ready":
                return result["result"]["sample"]
            elif result["status"] in [
                "Error",
                "Request Moderated",
                "Content Moderated",
            ]:
                raise Exception(f"Task failed with status: {result['status']}")
            await asyncio.sleep(check_interval)

        raise TimeoutError(
            f"Image generation timed out after {max_wait_time} seconds"
        )
    finally:
        await self._close_async_client()

batch_generate

batch_generate(prompts, **kwargs)

Generates images for a batch of prompts synchronously.

PARAMETER	DESCRIPTION
prompts	List of text prompts TYPE: List[str]
**kwargs	Additional arguments passed to generate_image TYPE: Dict[str, Any] DEFAULT: {}

RETURNS	DESCRIPTION
List[Dict]	List[Dict]: List of result dictionaries

Source code in swarmauri_standard/image_gens/BlackForestImgGenModel.py

def batch_generate(
    self, prompts: List[str], **kwargs: Dict[str, Any]
) -> List[Dict]:
    """
    Generates images for a batch of prompts synchronously.

    Args:
        prompts (List[str]): List of text prompts
        **kwargs (Dict[str, Any]): Additional arguments passed to generate_image

    Returns:
        List[Dict]: List of result dictionaries
    """
    return [self.generate_image(prompt=prompt, **kwargs) for prompt in prompts]

abatch_generate async

abatch_generate(prompts, max_concurrent=5, **kwargs)

Asynchronously generates images for a batch of prompts.

PARAMETER	DESCRIPTION
prompts	List of text prompts TYPE: List[str]
max_concurrent	Maximum number of concurrent tasks TYPE: int DEFAULT: 5
**kwargs	Additional arguments passed to agenerate_image TYPE: Dict[str, Any] DEFAULT: {}

RETURNS	DESCRIPTION
List[Dict]	List[Dict]: List of result dictionaries

Source code in swarmauri_standard/image_gens/BlackForestImgGenModel.py

async def abatch_generate(
    self, prompts: List[str], max_concurrent: int = 5, **kwargs: Dict[str, Any]
) -> List[Dict]:
    """
    Asynchronously generates images for a batch of prompts.

    Args:
        prompts (List[str]): List of text prompts
        max_concurrent (int): Maximum number of concurrent tasks
        **kwargs (Dict[str, Any]): Additional arguments passed to agenerate_image

    Returns:
        List[Dict]: List of result dictionaries
    """
    try:
        semaphore = asyncio.Semaphore(max_concurrent)

        async def process_prompt(prompt):
            async with semaphore:
                return await self.agenerate_image(prompt=prompt, **kwargs)

        tasks = [process_prompt(prompt) for prompt in prompts]
        return await asyncio.gather(*tasks)
    finally:
        await self._close_async_client()

get_allowed_models

get_allowed_models()

Queries the LLMProvider API endpoint to get the list of allowed models.

RETURNS	DESCRIPTION
List[str]	List[str]: List of allowed model names.

Source code in swarmauri_standard/image_gens/BlackForestImgGenModel.py

def get_allowed_models(self) -> List[str]:
    """
    Queries the LLMProvider API endpoint to get the list of allowed models.

    Returns:
        List[str]: List of allowed model names.
    """
    return ["flux-pro-1.1", "flux-pro", "flux-dev"]

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS	DESCRIPTION
Callable	A decorator function that registers the model class. TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER	DESCRIPTION
resource_type	The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used. TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None
type_name	An optional custom type name for the subtype. TYPE: Optional[str] DEFAULT: None

RETURNS	DESCRIPTION
Callable	A decorator function that registers the subtype. TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py

@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py

def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py

@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py

def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py

def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger