@weirdfingers/baseboards 0.9.6 → 0.9.7

package/templates/api/src/boards/generators/implementations/fal/audio/minimax_speech_2_6_turbo.py

@@ -1,221 +0,0 @@
-"""
-fal.ai MiniMax Speech 2.6 Turbo text-to-speech generator.
-
-Generate speech from text prompts using the MiniMax Speech-2.6 HD model,
-which leverages advanced AI techniques to create high-quality text-to-speech.
-
-Based on Fal AI's fal-ai/minimax/speech-2.6-turbo model.
-See: https://fal.ai/models/fal-ai/minimax/speech-2.6-turbo
-"""
-
-import os
-from typing import Literal
-
-from pydantic import BaseModel, Field
-
-from ....base import BaseGenerator, GeneratorExecutionContext, GeneratorResult
-
-
-class VoiceSetting(BaseModel):
-    """Voice configuration settings."""
-
-    voice_id: str = Field(
-        default="Wise_Woman",
-        description="Speaker identifier for the voice",
-    )
-    speed: float = Field(
-        default=1.0,
-        description="Playback speed multiplier",
-    )
-    pitch: float = Field(
-        default=0.0,
-        description="Pitch adjustment",
-    )
-    vol: float = Field(
-        default=1.0,
-        description="Volume level",
-    )
-    english_normalization: bool = Field(
-        default=False,
-        description="Enable English text normalization",
-    )
-
-
-class LoudnessNormalizationSetting(BaseModel):
-    """Audio loudness normalization controls."""
-
-    enabled: bool = Field(
-        default=True,
-        description="Enable loudness normalization",
-    )
-    target_loudness: float = Field(
-        default=-18.0,
-        ge=-70.0,
-        le=-10.0,
-        description="Target loudness in LUFS",
-    )
-    target_range: float = Field(
-        default=8.0,
-        ge=0.0,
-        le=20.0,
-        description="Target range in LU",
-    )
-    target_peak: float = Field(
-        default=-0.5,
-        ge=-3.0,
-        le=0.0,
-        description="Target peak level in dBTP",
-    )
-
-
-class MinimaxSpeech26TurboInput(BaseModel):
-    """Input schema for MiniMax Speech 2.6 Turbo generation."""
-
-    prompt: str = Field(
-        description=(
-            "Text to convert to speech (supports pause markers <#x#> with 0.01-99.99 seconds)"
-        ),
-        min_length=1,
-        max_length=10000,
-    )
-    voice_setting: VoiceSetting = Field(
-        default_factory=VoiceSetting,
-        description="Voice configuration including voice_id, speed, pitch, volume",
-    )
-    language_boost: str = Field(
-        default="auto",
-        description=(
-            "Enhance recognition of specified languages and dialects "
-            "(auto or specific language code)"
-        ),
-    )
-    output_format: Literal["url", "hex"] = Field(
-        default="url",
-        description="Output format: 'url' for audio file URL or 'hex' for hex-encoded data",
-    )
-    normalization_setting: LoudnessNormalizationSetting = Field(
-        default_factory=LoudnessNormalizationSetting,
-        description="Audio loudness normalization controls",
-    )
-
-
-class FalMinimaxSpeech26TurboGenerator(BaseGenerator):
-    """MiniMax Speech 2.6 Turbo text-to-speech generator using fal.ai."""
-
-    name = "fal-minimax-speech-2-6-turbo"
-    artifact_type = "audio"
-    description = (
-        "Fal: MiniMax Speech 2.6 Turbo - "
-        "High-quality text-to-speech with customizable voices and 35+ languages"
-    )
-
-    def get_input_schema(self) -> type[MinimaxSpeech26TurboInput]:
-        return MinimaxSpeech26TurboInput
-
-    async def generate(
-        self, inputs: MinimaxSpeech26TurboInput, context: GeneratorExecutionContext
-    ) -> GeneratorResult:
-        """Generate audio using fal.ai MiniMax Speech 2.6 Turbo model."""
-        # Check for API key (fal-client uses FAL_KEY environment variable)
-        if not os.getenv("FAL_KEY"):
-            raise ValueError("API configuration invalid. Missing FAL_KEY environment variable")
-
-        # Import fal_client
-        try:
-            import fal_client
-        except ImportError as e:
-            raise ImportError(
-                "fal.ai SDK is required for FalMinimaxSpeech26TurboGenerator. "
-                "Install with: pip install weirdfingers-boards[generators-fal]"
-            ) from e
-
-        # Prepare arguments for fal.ai API
-        arguments = {
-            "prompt": inputs.prompt,
-            "voice_setting": {
-                "voice_id": inputs.voice_setting.voice_id,
-                "speed": inputs.voice_setting.speed,
-                "pitch": inputs.voice_setting.pitch,
-                "vol": inputs.voice_setting.vol,
-                "english_normalization": inputs.voice_setting.english_normalization,
-            },
-            "language_boost": inputs.language_boost,
-            "output_format": inputs.output_format,
-            "normalization_setting": {
-                "enabled": inputs.normalization_setting.enabled,
-                "target_loudness": inputs.normalization_setting.target_loudness,
-                "target_range": inputs.normalization_setting.target_range,
-                "target_peak": inputs.normalization_setting.target_peak,
-            },
-        }
-
-        # Submit async job and get handler
-        handler = await fal_client.submit_async(
-            "fal-ai/minimax/speech-2.6-turbo",
-            arguments=arguments,
-        )
-
-        # Store the external job ID for tracking
-        await context.set_external_job_id(handler.request_id)
-
-        # Stream progress updates (sample every 3rd event to avoid spam)
-        from .....progress.models import ProgressUpdate
-
-        event_count = 0
-        async for event in handler.iter_events(with_logs=True):
-            event_count += 1
-
-            # Process every 3rd event to provide feedback without overwhelming
-            if event_count % 3 == 0:
-                # Extract logs if available
-                logs = getattr(event, "logs", None)
-                if logs:
-                    # Join log entries into a single message
-                    if isinstance(logs, list):
-                        message = " | ".join(str(log) for log in logs if log)
-                    else:
-                        message = str(logs)
-
-                    if message:
-                        await context.publish_progress(
-                            ProgressUpdate(
-                                job_id=handler.request_id,
-                                status="processing",
-                                progress=50.0,  # Approximate mid-point progress
-                                phase="processing",
-                                message=message,
-                            )
-                        )
-
-        # Get final result
-        result = await handler.get()
-
-        # Extract audio URL from result
-        # fal.ai returns: {"audio": {"url": "..."}}
-        audio_data = result.get("audio")
-        if audio_data is None:
-            raise ValueError("No audio data returned from fal.ai API")
-
-        audio_url = audio_data.get("url")
-        if not audio_url:
-            raise ValueError("Audio URL missing in fal.ai response")
-
-        # Store audio result
-        artifact = await context.store_audio_result(
-            storage_url=audio_url,
-            format="mp3",  # MiniMax Speech returns MP3 format
-            output_index=0,
-        )
-
-        return GeneratorResult(outputs=[artifact])
-
-    async def estimate_cost(self, inputs: MinimaxSpeech26TurboInput) -> float:
-        """Estimate cost for MiniMax Speech 2.6 Turbo generation.
-
-        MiniMax Speech 2.6 Turbo costs $0.06 per 1000 characters.
-        """
-        # Calculate character count
-        char_count = len(inputs.prompt)
-
-        # Cost is $0.06 per 1000 characters
-        return (char_count / 1000.0) * 0.06

package/templates/api/src/boards/generators/implementations/fal/image/__init__.py

@@ -1,63 +0,0 @@
-"""Fal.ai image generators."""
-
-from .bytedance_seedream_v45_edit import FalBytedanceSeedreamV45EditGenerator
-from .clarity_upscaler import FalClarityUpscalerGenerator
-from .crystal_upscaler import FalCrystalUpscalerGenerator
-from .fal_ideogram_character import FalIdeogramCharacterGenerator
-from .flux_2 import FalFlux2Generator
-from .flux_2_edit import FalFlux2EditGenerator
-from .flux_2_pro import FalFlux2ProGenerator
-from .flux_2_pro_edit import FalFlux2ProEditGenerator
-from .flux_pro_kontext import FalFluxProKontextGenerator
-from .flux_pro_ultra import FalFluxProUltraGenerator
-from .gemini_25_flash_image import FalGemini25FlashImageGenerator
-from .gemini_25_flash_image_edit import FalGemini25FlashImageEditGenerator
-from .gpt_image_1_5 import FalGptImage15Generator
-from .gpt_image_1_edit_image import FalGptImage1EditImageGenerator
-from .gpt_image_1_mini import FalGptImage1MiniGenerator
-from .gpt_image_15_edit import FalGptImage15EditGenerator
-from .ideogram_character_edit import FalIdeogramCharacterEditGenerator
-from .ideogram_v2 import FalIdeogramV2Generator
-from .imagen4_preview import FalImagen4PreviewGenerator
-from .imagen4_preview_fast import FalImagen4PreviewFastGenerator
-from .nano_banana import FalNanoBananaGenerator
-from .nano_banana_edit import FalNanoBananaEditGenerator
-from .nano_banana_pro import FalNanoBananaProGenerator
-from .nano_banana_pro_edit import FalNanoBananaProEditGenerator
-from .qwen_image import FalQwenImageGenerator
-from .qwen_image_edit import FalQwenImageEditGenerator
-from .reve_edit import FalReveEditGenerator
-from .reve_text_to_image import FalReveTextToImageGenerator
-from .seedream_v45_text_to_image import FalSeedreamV45TextToImageGenerator
-
-__all__ = [
-    "FalBytedanceSeedreamV45EditGenerator",
-    "FalClarityUpscalerGenerator",
-    "FalCrystalUpscalerGenerator",
-    "FalFlux2Generator",
-    "FalFlux2EditGenerator",
-    "FalFlux2ProGenerator",
-    "FalFlux2ProEditGenerator",
-    "FalFluxProKontextGenerator",
-    "FalFluxProUltraGenerator",
-    "FalGemini25FlashImageEditGenerator",
-    "FalGemini25FlashImageGenerator",
-    "FalGptImage15EditGenerator",
-    "FalGptImage15Generator",
-    "FalGptImage1EditImageGenerator",
-    "FalGptImage1MiniGenerator",
-    "FalIdeogramCharacterGenerator",
-    "FalIdeogramCharacterEditGenerator",
-    "FalIdeogramV2Generator",
-    "FalImagen4PreviewGenerator",
-    "FalImagen4PreviewFastGenerator",
-    "FalNanoBananaGenerator",
-    "FalNanoBananaEditGenerator",
-    "FalNanoBananaProGenerator",
-    "FalNanoBananaProEditGenerator",
-    "FalQwenImageEditGenerator",
-    "FalQwenImageGenerator",
-    "FalReveEditGenerator",
-    "FalReveTextToImageGenerator",
-    "FalSeedreamV45TextToImageGenerator",
-]

package/templates/api/src/boards/generators/implementations/fal/image/bytedance_seedream_v45_edit.py

@@ -1,219 +0,0 @@
-"""
-fal.ai ByteDance Seedream v4.5 Edit image editing generator.
-
-Edit images using fal.ai's ByteDance Seedream v4.5 Edit model.
-A new-generation image creation model that integrates image generation
-and image editing capabilities into a single, unified architecture.
-Supports editing up to 10 input images with a text prompt.
-
-See: https://fal.ai/models/fal-ai/bytedance/seedream/v4.5/edit
-"""
-
-import os
-from typing import Literal
-
-from pydantic import BaseModel, Field
-
-from ....artifacts import ImageArtifact
-from ....base import BaseGenerator, GeneratorExecutionContext, GeneratorResult
-
-# Valid image size presets
-ImageSizePreset = Literal[
-    "square_hd",
-    "square",
-    "portrait_4_3",
-    "portrait_16_9",
-    "landscape_4_3",
-    "landscape_16_9",
-    "auto_2K",
-    "auto_4K",
-]
-
-
-class BytedanceSeedreamV45EditInput(BaseModel):
-    """Input schema for ByteDance Seedream v4.5 Edit.
-
-    Artifact fields (like image_sources) are automatically detected via type
-    introspection and resolved from generation IDs to ImageArtifact objects.
-    """
-
-    prompt: str = Field(description="The text prompt used to edit the image")
-    image_sources: list[ImageArtifact] = Field(
-        description="List of input images for editing (up to 10 images)",
-        min_length=1,
-        max_length=10,
-    )
-    num_images: int = Field(
-        default=1,
-        ge=1,
-        le=6,
-        description="Number of images to generate",
-    )
-    image_size: ImageSizePreset | None = Field(
-        default=None,
-        description=(
-            "The size of the generated image. Options: square_hd, square, "
-            "portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9, "
-            "auto_2K, auto_4K. Default is 2048x2048"
-        ),
-    )
-    seed: int | None = Field(
-        default=None,
-        description="Random seed to control the stochasticity of image generation",
-    )
-    sync_mode: bool = Field(
-        default=False,
-        description=(
-            "If True, the media will be returned as a data URI and the output "
-            "data won't be available in the request history"
-        ),
-    )
-    enable_safety_checker: bool = Field(
-        default=True,
-        description="Enables safety filtering on generated images",
-    )
-
-
-class FalBytedanceSeedreamV45EditGenerator(BaseGenerator):
-    """ByteDance Seedream v4.5 Edit image editing generator using fal.ai."""
-
-    name = "fal-bytedance-seedream-v45-edit"
-    artifact_type = "image"
-    description = "Fal: ByteDance Seedream v4.5 Edit - Unified image generation and editing"
-
-    def get_input_schema(self) -> type[BytedanceSeedreamV45EditInput]:
-        return BytedanceSeedreamV45EditInput
-
-    async def generate(
-        self, inputs: BytedanceSeedreamV45EditInput, context: GeneratorExecutionContext
-    ) -> GeneratorResult:
-        """Edit images using fal.ai ByteDance Seedream v4.5 Edit model."""
-        # Check for API key (fal-client uses FAL_KEY environment variable)
-        if not os.getenv("FAL_KEY"):
-            raise ValueError("API configuration invalid. Missing FAL_KEY environment variable")
-
-        # Import fal_client
-        try:
-            import fal_client
-        except ImportError as e:
-            raise ImportError(
-                "fal.ai SDK is required for FalBytedanceSeedreamV45EditGenerator. "
-                "Install with: pip install weirdfingers-boards[generators-fal]"
-            ) from e
-
-        # Upload image artifacts to Fal's public storage
-        # Fal API requires publicly accessible URLs, but our storage_url might be:
-        # - Localhost URLs (not publicly accessible)
-        # - Private S3 buckets (not publicly accessible)
-        # So we upload to Fal's temporary storage first
-        from ..utils import upload_artifacts_to_fal
-
-        image_urls = await upload_artifacts_to_fal(inputs.image_sources, context)
-
-        # Prepare arguments for fal.ai API
-        arguments: dict = {
-            "prompt": inputs.prompt,
-            "image_urls": image_urls,
-            "num_images": inputs.num_images,
-            "sync_mode": inputs.sync_mode,
-            "enable_safety_checker": inputs.enable_safety_checker,
-        }
-
-        # Add optional parameters
-        if inputs.image_size is not None:
-            arguments["image_size"] = inputs.image_size
-
-        if inputs.seed is not None:
-            arguments["seed"] = inputs.seed
-
-        # Submit async job and get handler
-        handler = await fal_client.submit_async(
-            "fal-ai/bytedance/seedream/v4.5/edit",
-            arguments=arguments,
-        )
-
-        # Store the external job ID for tracking
-        await context.set_external_job_id(handler.request_id)
-
-        # Stream progress updates (sample every 3rd event to avoid spam)
-        from .....progress.models import ProgressUpdate
-
-        event_count = 0
-        async for event in handler.iter_events(with_logs=True):
-            event_count += 1
-
-            # Process every 3rd event to provide feedback without overwhelming
-            if event_count % 3 == 0:
-                # Extract logs if available
-                logs = getattr(event, "logs", None)
-                if logs:
-                    # Join log entries into a single message
-                    if isinstance(logs, list):
-                        message = " | ".join(str(log) for log in logs if log)
-                    else:
-                        message = str(logs)
-
-                    if message:
-                        await context.publish_progress(
-                            ProgressUpdate(
-                                job_id=handler.request_id,
-                                status="processing",
-                                progress=50.0,  # Approximate mid-point progress
-                                phase="processing",
-                                message=message,
-                            )
-                        )
-
-        # Get final result
-        result = await handler.get()
-
-        # Extract image URLs from result
-        # fal.ai returns: {
-        #   "images": [{"url": "...", "width": ..., "height": ..., ...}, ...]
-        # }
-        images = result.get("images", [])
-
-        if not images:
-            raise ValueError("No images returned from fal.ai API")
-
-        # Store each image using output_index
-        artifacts = []
-        for idx, image_data in enumerate(images):
-            image_url = image_data.get("url")
-            # Extract dimensions if available, otherwise use sensible defaults
-            width = image_data.get("width", 2048)
-            height = image_data.get("height", 2048)
-
-            if not image_url:
-                raise ValueError(f"Image {idx} missing URL in fal.ai response")
-
-            # Determine format from content_type or default to png
-            content_type = image_data.get("content_type", "image/png")
-            if "jpeg" in content_type or "jpg" in content_type:
-                format_type = "jpeg"
-            elif "webp" in content_type:
-                format_type = "webp"
-            else:
-                format_type = "png"
-
-            # Store with appropriate output_index
-            artifact = await context.store_image_result(
-                storage_url=image_url,
-                format=format_type,
-                width=width,
-                height=height,
-                output_index=idx,
-            )
-            artifacts.append(artifact)
-
-        return GeneratorResult(outputs=artifacts)
-
-    async def estimate_cost(self, inputs: BytedanceSeedreamV45EditInput) -> float:
-        """Estimate cost for ByteDance Seedream v4.5 Edit generation.
-
-        Pricing not disclosed in documentation, using conservative estimate
-        based on similar high-quality image editing models.
-        """
-        # Conservative estimate per image
-        per_image_cost = 0.05
-        return per_image_cost * inputs.num_images