refactor image methods

Signed-off-by: vladmandic <mandic00@live.com>

modules/postprocess/pixelart.py

@@ -9,8 +9,8 @@ from diffusers.image_processor import PipelineImageInput
 from diffusers.configuration_utils import ConfigMixin, register_to_config
 from transformers import ImageProcessingMixin
 
-from modules import images_sharpfin
 from modules import devices
+from modules.image import sharpfin
 
 
 @devices.inference_context()
@@ -64,9 +64,9 @@ def edge_detect_for_pixelart(image: PipelineImageInput, image_weight: float = 1.
     greyscale_reshaped = greyscale_reshaped.reshape(batch_size, block_size_sq, block_height, block_width)
 
     greyscale_range = greyscale_reshaped.amax(dim=1, keepdim=True).sub_(greyscale_reshaped.amin(dim=1, keepdim=True))
-    range_weight = images_sharpfin.resize_tensor(greyscale_range, (height, width), linearize=False)
+    range_weight = sharpfin.resize_tensor(greyscale_range, (height, width), linearize=False)
     range_weight = range_weight.div_(range_weight.max())
-    weight_map = images_sharpfin.resize_tensor((greyscale > greyscale.median()).to(dtype=torch.float32), (height, width), linearize=False)
+    weight_map = sharpfin.resize_tensor((greyscale > greyscale.median()).to(dtype=torch.float32), (height, width), linearize=False)
     weight_map = weight_map.unsqueeze(0).add_(range_weight).mul_(image_weight / 2)
 
     new_image = new_image.mul_(weight_map).addcmul_(min_pool, (1-weight_map))
@@ -158,7 +158,7 @@ def encode_jpeg_tensor(img: torch.FloatTensor, block_size: int=16, cbcr_downscal
     img = img[:, :, :(img.shape[-2]//block_size)*block_size, :(img.shape[-1]//block_size)*block_size] # crop to a multiply of block_size
     cbcr_block_size = block_size//cbcr_downscale
     _, _, height, width = img.shape
-    down_img = images_sharpfin.resize_tensor(img[:, 1:,:,:], (height//cbcr_downscale, width//cbcr_downscale), linearize=False)
+    down_img = sharpfin.resize_tensor(img[:, 1:,:,:], (height//cbcr_downscale, width//cbcr_downscale), linearize=False)
     y = encode_single_channel_dct_2d(img[:, 0, :,:], block_size=block_size, norm=norm)
     cb = encode_single_channel_dct_2d(down_img[:, 0, :,:], block_size=cbcr_block_size, norm=norm)
     cr = encode_single_channel_dct_2d(down_img[:, 1, :,:], block_size=cbcr_block_size, norm=norm)
@@ -176,8 +176,8 @@ def decode_jpeg_tensor(jpeg_img: torch.FloatTensor, block_size: int=16, cbcr_dow
     y = decode_single_channel_dct_2d(y, norm=norm)
     cb = decode_single_channel_dct_2d(cb, norm=norm)
     cr = decode_single_channel_dct_2d(cr, norm=norm)
-    cb = images_sharpfin.resize_tensor(cb, (h_blocks*block_size, w_blocks*block_size), linearize=False)
-    cr = images_sharpfin.resize_tensor(cr, (h_blocks*block_size, w_blocks*block_size), linearize=False)
+    cb = sharpfin.resize_tensor(cb, (h_blocks*block_size, w_blocks*block_size), linearize=False)
+    cr = sharpfin.resize_tensor(cr, (h_blocks*block_size, w_blocks*block_size), linearize=False)
     return torch.stack([y,cb,cr], dim=1)
 
 

modules/postprocess/seedvr_model.py

@@ -3,9 +3,10 @@ import random
 import numpy as np
 import torch
 from PIL import Image
-from modules import devices, images_sharpfin
+from modules import devices
 from modules.shared import opts, log
 from modules.upscaler import Upscaler, UpscalerData
+from modules.image import convert
 
 
 MODELS_MAP = {
@@ -13,7 +14,6 @@ MODELS_MAP = {
     "SeedVR2 7B": "seedvr2_ema_7b_fp16.safetensors",
     "SeedVR2 7B Sharp": "seedvr2_ema_7b_sharp_fp16.safetensors",
 }
-to_pil = images_sharpfin.to_pil
 
 
 class UpscalerSeedVR(Upscaler):
@@ -158,7 +158,7 @@ class UpscalerSeedVR(Upscaler):
             )
         t1 = time.time()
         log.info(f'Upscaler: type="{self.name}" model="{selected_file}" scale={self.scale} cfg={opts.seedvt_cfg_scale} seed={seed} time={t1 - t0:.2f}')
-        img = to_pil(result_tensor.squeeze())
+        img = convert.to_pil(result_tensor.squeeze())
 
         if opts.upscaler_unload:
             self.model.dit = None