# handler.py import torch from diffusers import DiffusionPipeline # check for GPU device = 0 if torch.cuda.is_available() else -1 # multi-model list multi_model_list = [ {"model_id": "dreamlike-art/dreamlike-photoreal-2.0", "task": "text-to-image"}, {"model_id": "Lykon/DreamShaper", "task": "text-to-image"}, {"model_id": "Envvi/Inkpunk-Diffusion", "task": "text-to-image"}, # Add other models if needed ] class EndpointHandler(): def __init__(self, path=""): self.multi_model = {} # load all the models for model in multi_model_list: self.multi_model[model["model_id"]] = DiffusionPipeline.from_pretrained(model["model_id"]) def __call__(self, data): # deserialize incoming request inputs = data.pop("inputs", data) parameters = data.pop("parameters", None) model_id = data.pop("model_id", None) # check if model_id is in the list of models if model_id is None or model_id not in self.multi_model: raise ValueError(f"model_id: {model_id} is not valid. Available models are: {list(self.multi_model.keys())}") # move the model to the appropriate device before making predictions self.multi_model[model_id].to(device) # pass inputs with all kwargs in data if parameters is not None: prediction = self.multi_model[model_id](inputs, **parameters) else: prediction = self.multi_model[model_id](inputs) # postprocess the prediction return prediction