add DiffusionInpaintModel

lama_cleaner/model/paint_by_example.py

@@ -1,19 +1,16 @@
-import random
-
 import PIL
 import PIL.Image
 import cv2
-import numpy as np
 import torch
 from diffusers import DiffusionPipeline
 from loguru import logger
 
-from lama_cleaner.helper import resize_max_size
-from lama_cleaner.model.base import InpaintModel
+from lama_cleaner.model.base import DiffusionInpaintModel
+from lama_cleaner.model.utils import set_seed
 from lama_cleaner.schema import Config
 
 
-class PaintByExample(InpaintModel):
+class PaintByExample(DiffusionInpaintModel):
     pad_mod = 8
     min_size = 512
 
@@ -53,11 +50,7 @@ class PaintByExample(InpaintModel):
         mask: [H, W, 1] 255 means area to repaint
         return: BGR IMAGE
         """
-        seed = config.paint_by_example_seed
-        random.seed(seed)
-        np.random.seed(seed)
-        torch.manual_seed(seed)
-        torch.cuda.manual_seed_all(seed)
+        set_seed(config.paint_by_example_seed)
 
         output = self.model(
             image=PIL.Image.fromarray(image),
@@ -71,42 +64,6 @@ class PaintByExample(InpaintModel):
         output = cv2.cvtColor(output, cv2.COLOR_RGB2BGR)
         return output
 
-    def _scaled_pad_forward(self, image, mask, config: Config):
-        longer_side_length = int(config.sd_scale * max(image.shape[:2]))
-        origin_size = image.shape[:2]
-        downsize_image = resize_max_size(image, size_limit=longer_side_length)
-        downsize_mask = resize_max_size(mask, size_limit=longer_side_length)
-        logger.info(
-            f"Resize image to do paint_by_example: {image.shape} -> {downsize_image.shape}"
-        )
-        inpaint_result = self._pad_forward(downsize_image, downsize_mask, config)
-        # only paste masked area result
-        inpaint_result = cv2.resize(
-            inpaint_result,
-            (origin_size[1], origin_size[0]),
-            interpolation=cv2.INTER_CUBIC,
-        )
-        original_pixel_indices = mask < 127
-        inpaint_result[original_pixel_indices] = image[:, :, ::-1][original_pixel_indices]
-        return inpaint_result
-
-    @torch.no_grad()
-    def __call__(self, image, mask, config: Config):
-        """
-        images: [H, W, C] RGB, not normalized
-        masks: [H, W]
-        return: BGR IMAGE
-        """
-        if config.use_croper:
-            crop_img, crop_mask, (l, t, r, b) = self._apply_cropper(image, mask, config)
-            crop_image = self._scaled_pad_forward(crop_img, crop_mask, config)
-            inpaint_result = image[:, :, ::-1]
-            inpaint_result[t:b, l:r, :] = crop_image
-        else:
-            inpaint_result = self._scaled_pad_forward(image, mask, config)
-
-        return inpaint_result
-
     def forward_post_process(self, result, image, mask, config):
         if config.paint_by_example_match_histograms:
             result = self._match_histograms(result, image[:, :, ::-1], mask)