Update utils.py

utils.py

@@ -3,19 +3,12 @@ import os
 import random
 import numpy as np
 import json
-import torch
 import uuid
 from PIL import Image, PngImagePlugin
 from datetime import datetime
 from dataclasses import dataclass
 from typing import Callable, Dict, Optional, Tuple
-from diffusers import (
-    DDIMScheduler,
-    DPMSolverMultistepScheduler,
-    DPMSolverSinglestepScheduler,
-    EulerAncestralDiscreteScheduler,
-    EulerDiscreteScheduler,
-)
+
 
 MAX_SEED = np.iinfo(np.int32).max
 
@@ -32,14 +25,6 @@ def randomize_seed_fn(seed: int, randomize_seed: bool) -> int:
     return seed
 
 
-def seed_everything(seed: int) -> torch.Generator:
-    torch.manual_seed(seed)
-    torch.cuda.manual_seed_all(seed)
-    np.random.seed(seed)
-    generator = torch.Generator()
-    generator.manual_seed(seed)
-    return generator
-
 
 def parse_aspect_ratio(aspect_ratio: str) -> Optional[Tuple[int, int]]:
     if aspect_ratio == "Custom":
@@ -58,24 +43,6 @@ def aspect_ratio_handler(
         return width, height
 
 
-def get_scheduler(scheduler_config: Dict, name: str) -> Optional[Callable]:
-    scheduler_factory_map = {
-        "DPM++ 2M Karras": lambda: DPMSolverMultistepScheduler.from_config(
-            scheduler_config, use_karras_sigmas=True
-        ),
-        "DPM++ SDE Karras": lambda: DPMSolverSinglestepScheduler.from_config(
-            scheduler_config, use_karras_sigmas=True
-        ),
-        "DPM++ 2M SDE Karras": lambda: DPMSolverMultistepScheduler.from_config(
-            scheduler_config, use_karras_sigmas=True, algorithm_type="sde-dpmsolver++"
-        ),
-        "Euler": lambda: EulerDiscreteScheduler.from_config(scheduler_config),
-        "Euler a": lambda: EulerAncestralDiscreteScheduler.from_config(
-            scheduler_config
-        ),
-        "DDIM": lambda: DDIMScheduler.from_config(scheduler_config),
-    }
-    return scheduler_factory_map.get(name, lambda: None)()
 
 
 def free_memory() -> None:
@@ -107,25 +74,6 @@ def preprocess_prompt(
     return formatted_positive, combined_negative
 
 
-def common_upscale(
-    samples: torch.Tensor,
-    width: int,
-    height: int,
-    upscale_method: str,
-) -> torch.Tensor:
-    return torch.nn.functional.interpolate(
-        samples, size=(height, width), mode=upscale_method
-    )
-
-
-def upscale(
-    samples: torch.Tensor, upscale_method: str, scale_by: float
-) -> torch.Tensor:
-    width = round(samples.shape[3] * scale_by)
-    height = round(samples.shape[2] * scale_by)
-    return common_upscale(samples, width, height, upscale_method)
-
-
 
 def get_random_line_from_file(file_path: str) -> str:
     with open(file_path, "r") as file: