File size: 1,606 Bytes
83283ea 69c97e9 83283ea |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
from typing import Dict, List, Any
from tangoflux import TangoFluxInference
import torchaudio
#from huggingface_inference_toolkit.logging import logger
class EndpointHandler():
def __init__(self, path=""):
# Preload all the elements you are going to need at inference.
# pseudo:
# self.model= load_model(path)
self.model = TangoFluxInference(name='declare-lab/TangoFlux',device='cuda')
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
"""
data args:
inputs (:obj: `str` | `PIL.Image` | `np.array`)
kwargs
Return:
A :obj:`list` | `dict`: will be serialized and returned
"""
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 audio generation, and it needs to be a non-empty string."
)
parameters = data.pop("parameters", {})
num_inference_steps = parameters.get("num_inference_steps", 50)
duration = parameters.get("duration", 10)
guidance_scale = parameters.get("guidance_scale", 3.5)
return self.model.generate(prompt,steps=num_inference_steps,
duration=duration,
guidance_scale=guidance_scale) |