Merge pull request #4459 from kavorite/color-sketch-inpainting

add `--gradio-inpaint-tool` and option to specify `color-sketch`

3 files changed, 36 insertions, 10 deletions

diff --git a/modules/img2img.py b/modules/img2img.py
index 7e58994a..830cfa15 100644
--- a/modules/img2img.py
+++ b/modules/img2img.py
@@ -4,7 +4,7 @@ import sys
 import traceback

 

 import numpy as np

-from PIL import Image, ImageOps, ImageChops

+from PIL import Image, ImageOps, ImageFilter, ImageEnhance

 

 from modules import devices, sd_samplers

 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images

@@ -40,7 +40,7 @@ def process_batch(p, input_dir, output_dir, args):
 

         img = Image.open(image)

         # Use the EXIF orientation of photos taken by smartphones.

-        img = ImageOps.exif_transpose(img) 

+        img = ImageOps.exif_transpose(img)

         p.init_images = [img] * p.batch_size

 

         proc = modules.scripts.scripts_img2img.run(p, *args)

@@ -59,18 +59,30 @@ def process_batch(p, input_dir, output_dir, args):
                 processed_image.save(os.path.join(output_dir, filename))

 

 

-def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, init_img, init_img_with_mask, init_img_inpaint, init_mask_inpaint, mask_mode, steps: int, sampler_index: int, mask_blur: int, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, *args):

+def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, prompt_style2: str, init_img, init_img_with_mask, init_img_with_mask_orig, init_img_inpaint, init_mask_inpaint, mask_mode, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, *args):

     is_inpaint = mode == 1

     is_batch = mode == 2

 

     if is_inpaint:

         # Drawn mask

         if mask_mode == 0:

-            image = init_img_with_mask['image']

-            mask = init_img_with_mask['mask']

-            alpha_mask = ImageOps.invert(image.split()[-1]).convert('L').point(lambda x: 255 if x > 0 else 0, mode='1')

-            mask = ImageChops.lighter(alpha_mask, mask.convert('L')).convert('L')

-            image = image.convert('RGB')

+            image = init_img_with_mask

+            is_mask_sketch = isinstance(image, dict)

+            is_mask_paint = not is_mask_sketch

+            if is_mask_sketch:

+                # Sketch: mask iff. not transparent

+                image, mask = image["image"], image["mask"]

+                pred = np.array(mask)[..., -1] > 0

+            else:

+                # Color-sketch: mask iff. painted over

+                orig = init_img_with_mask_orig or image

+                pred = np.any(np.array(image) != np.array(orig), axis=-1)

+            mask = Image.fromarray(pred.astype(np.uint8) * 255, "L")

+            if is_mask_paint:

+                mask = ImageEnhance.Brightness(mask).enhance(1 - mask_alpha / 100)

+                blur = ImageFilter.GaussianBlur(mask_blur)

+                image = Image.composite(image.filter(blur), orig, mask.filter(blur))

+            image = image.convert("RGB")

         # Uploaded mask

         else:

             image = init_img_inpaint

@@ -82,7 +94,7 @@ def img2img(mode: int, prompt: str, negative_prompt: str, prompt_style: str, pro
 

     # Use the EXIF orientation of photos taken by smartphones.

     if image is not None:

-        image = ImageOps.exif_transpose(image) 

+        image = ImageOps.exif_transpose(image)

 

     assert 0. <= denoising_strength <= 1., 'can only work with strength in [0.0, 1.0]'

 

diff --git a/modules/shared.py b/modules/shared.py
index 42ec4120..8202d8e5 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -72,6 +72,7 @@ parser.add_argument("--ui-settings-file", type=str, help="filename to use for ui
 parser.add_argument("--gradio-debug",  action='store_true', help="launch gradio with --debug option")

 parser.add_argument("--gradio-auth", type=str, help='set gradio authentication like "username:password"; or comma-delimit multiple like "u1:p1,u2:p2,u3:p3"', default=None)

 parser.add_argument("--gradio-img2img-tool", type=str, help='gradio image uploader tool: can be either editor for ctopping, or color-sketch for drawing', choices=["color-sketch", "editor"], default="editor")

+parser.add_argument("--gradio-inpaint-tool", type=str, choices=["sketch", "color-sketch"], default="sketch", help="gradio inpainting editor: can be either sketch to only blur/noise the input, or color-sketch to paint over it")

 parser.add_argument("--opt-channelslast", action='store_true', help="change memory type for stable diffusion to channels last")

 parser.add_argument("--styles-file", type=str, help="filename to use for styles", default=os.path.join(script_path, 'styles.csv'))

 parser.add_argument("--autolaunch", action='store_true', help="open the webui URL in the system's default browser upon launch", default=False)

diff --git a/modules/ui.py b/modules/ui.py
index 00809361..2eb0b684 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -792,11 +792,22 @@ def create_ui():
                         init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_img2img_tool).style(height=480)

 

                     with gr.TabItem('Inpaint', id='inpaint'):

-                        init_img_with_mask = gr.Image(label="Image for inpainting with mask",  show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", image_mode="RGBA").style(height=480)

+                        init_img_with_mask_orig = gr.State(None)

+                        init_img_with_mask = gr.Image(label="Image for inpainting with mask", show_label=False, elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool=cmd_opts.gradio_inpaint_tool, image_mode="RGBA").style(height=480)

 

+                        def update_orig(image, state):

+                            if image is not None:

+                                same_size = state is not None and state.size == image.size

+                                has_exact_match = np.any(np.all(np.array(image) == np.array(state), axis=-1))

+                                edited = same_size and has_exact_match

+                                return image if not edited or state is None else state

+

+                        init_img_with_mask.change(update_orig, [init_img_with_mask, init_img_with_mask_orig], init_img_with_mask_orig)

                         init_img_inpaint = gr.Image(label="Image for img2img", show_label=False, source="upload", interactive=True, type="pil", visible=False, elem_id="img_inpaint_base")

                         init_mask_inpaint = gr.Image(label="Mask", source="upload", interactive=True, type="pil", visible=False, elem_id="img_inpaint_mask")

 

+                        show_mask_alpha = cmd_opts.gradio_inpaint_tool == "color-sketch"

+                        mask_alpha = gr.Slider(label="Mask transparency", interactive=show_mask_alpha, visible=show_mask_alpha)

                         mask_blur = gr.Slider(label='Mask blur', minimum=0, maximum=64, step=1, value=4)

 

                         with gr.Row():

@@ -884,12 +895,14 @@ def create_ui():
                     img2img_prompt_style2,

                     init_img,

                     init_img_with_mask,

+                    init_img_with_mask_orig,

                     init_img_inpaint,

                     init_mask_inpaint,

                     mask_mode,

                     steps,

                     sampler_index,

                     mask_blur,

+                    mask_alpha,

                     inpainting_fill,

                     restore_faces,

                     tiling,