handler.py

import os
from typing import Any, Dict

from diffusers import DiffusionPipeline  # type: ignore
from PIL.Image import Image
import torch

from huggingface_inference_toolkit.logging import logger


class EndpointHandler:
    def __init__(self, model_dir: str, **kwargs: Any) -> None:  # type: ignore
        """The current `EndpointHandler` works with any FLUX.1-dev LoRA Adapter."""
        if os.getenv("HF_TOKEN") is None:
            raise ValueError(
                "Since `black-forest-labs/FLUX.1-dev` is a gated model, you will need to provide a valid "
                "`HF_TOKEN` as an environment variable for the handler to work properly."
            )

        self.pipeline = DiffusionPipeline.from_pretrained(
            "black-forest-labs/FLUX.1-dev",
            torch_dtype=torch.bfloat16,
            token=os.getenv("HF_TOKEN"),
        )
        self.pipeline.load_lora_weights(model_dir)
        self.pipeline.to("cuda")

    def __call__(self, data: Dict[str, Any]) -> Image:
        logger.info(f"Received incoming request with {data=}")

        if "inputs" in data and isinstance(data["inputs"], str):
            prompt = data.pop("inputs")
        elif "prompt" in data and isinstance(data["prompt"], str):
            prompt = data.pop("prompt")
        else:
            raise ValueError(
                "Provided input body must contain either the key `inputs` or `prompt` with the"
                " prompt to use for the image generation, and it needs to be a non-empty string."
            )

        parameters = data.pop("parameters", {})

        num_inference_steps = parameters.get("num_inference_steps", 30)
        width = parameters.get("width", 1024)
        height = parameters.get("height", 768)
        guidance_scale = parameters.get("guidance_scale", 3.5)

        # seed generator (seed cannot be provided as is but via a generator)
        seed = parameters.get("seed", 0)
        generator = torch.manual_seed(seed)

        return self.pipeline(  # type: ignore
            prompt,
            height=height,
            width=width,
            guidance_scale=guidance_scale,
            num_inference_steps=num_inference_steps,
            generator=generator,
        ).images[0]