diff --git a/modules/esrgan_model.py b/modules/esrgan_model.py
index 3dcef5a6e..2ed1d2739 100644
--- a/modules/esrgan_model.py
+++ b/modules/esrgan_model.py
@@ -14,8 +14,11 @@ import modules.images
 
 def load_model(filename):
     # this code is adapted from https://github.com/xinntao/ESRGAN
-
-    pretrained_net = torch.load(filename)
+    if torch.has_mps:
+        map_l = 'cpu'
+    else:
+        map_l = None
+    pretrained_net = torch.load(filename, map_location=map_l)
     crt_model = arch.RRDBNet(3, 3, 64, 23, gc=32)
 
     if 'conv_first.weight' in pretrained_net:
diff --git a/modules/img2img.py b/modules/img2img.py
index 3129798da..c23923050 100644
--- a/modules/img2img.py
+++ b/modules/img2img.py
@@ -1,5 +1,7 @@
 import math
-from PIL import Image
+import cv2
+import numpy as np
+from PIL import Image, ImageOps, ImageChops
 
 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, state
@@ -16,7 +18,9 @@ def img2img(prompt: str, init_img, init_img_with_mask, steps: int, sampler_index
 
     if is_inpaint:
         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, init_img_with_mask['mask'].convert('L')).convert('RGBA')
+        image = image.convert('RGB')
     else:
         image = init_img
         mask = None
@@ -57,8 +61,19 @@ def img2img(prompt: str, init_img, init_img_with_mask, steps: int, sampler_index
 
         state.job_count = n_iter
 
+        do_color_correction = False
+        try:
+            from skimage import exposure
+            do_color_correction = True
+        except:
+            print("Install scikit-image to perform color correction on loopback")
+
+
         for i in range(n_iter):
 
+            if do_color_correction and i == 0:
+                correction_target = cv2.cvtColor(np.asarray(init_img.copy()), cv2.COLOR_RGB2LAB)
+
             p.n_iter = 1
             p.batch_size = 1
             p.do_not_save_grid = True
@@ -69,8 +84,20 @@ def img2img(prompt: str, init_img, init_img_with_mask, steps: int, sampler_index
             if initial_seed is None:
                 initial_seed = processed.seed
                 initial_info = processed.info
+            
+            init_img = processed.images[0]
 
-            p.init_images = [processed.images[0]]
+            if do_color_correction and correction_target is not None:
+                init_img = Image.fromarray(cv2.cvtColor(exposure.match_histograms(
+                    cv2.cvtColor(
+                        np.asarray(init_img),
+                        cv2.COLOR_RGB2LAB
+                    ),
+                    correction_target,
+                    channel_axis=2
+                ), cv2.COLOR_LAB2RGB).astype("uint8"))
+
+            p.init_images = [init_img]
             p.seed = processed.seed + 1
             p.denoising_strength = max(p.denoising_strength * 0.95, 0.1)
             history.append(processed.images[0])
diff --git a/modules/lowvram.py b/modules/lowvram.py
index 4b78deab7..bd1174915 100644
--- a/modules/lowvram.py
+++ b/modules/lowvram.py
@@ -2,9 +2,12 @@ import torch
 
 module_in_gpu = None
 cpu = torch.device("cpu")
-gpu = torch.device("cuda")
-device = gpu if torch.cuda.is_available() else cpu
-
+if torch.has_cuda:
+    device = gpu = torch.device("cuda")
+elif torch.has_mps:
+    device = gpu = torch.device("mps")
+else:
+    device = gpu = torch.device("cpu")
 
 def setup_for_low_vram(sd_model, use_medvram):
     parents = {}
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py
index 2d26b5f71..1084e2484 100644
--- a/modules/sd_hijack.py
+++ b/modules/sd_hijack.py
@@ -232,7 +232,7 @@ class FrozenCLIPEmbedderWithCustomWords(torch.nn.Module):
         z = outputs.last_hidden_state
 
         # restoring original mean is likely not correct, but it seems to work well to prevent artifacts that happen otherwise
-        batch_multipliers = torch.asarray(np.array(batch_multipliers)).to(device)
+        batch_multipliers = torch.asarray(batch_multipliers).to(device)
         original_mean = z.mean()
         z *= batch_multipliers.reshape(batch_multipliers.shape + (1,)).expand(z.shape)
         new_mean = z.mean()
diff --git a/modules/shared.py b/modules/shared.py
index beb6f9bb0..e529ec27a 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -36,9 +36,12 @@ parser.add_argument("--opt-split-attention", action='store_true', help="enable o
 parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
 cmd_opts = parser.parse_args()
 
-cpu = torch.device("cpu")
-gpu = torch.device("cuda")
-device = gpu if torch.cuda.is_available() else cpu
+if torch.has_cuda:
+    device = torch.device("cuda")
+elif torch.has_mps:
+    device = torch.device("mps")
+else:
+    device = torch.device("cpu")
 batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)
 parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
 
diff --git a/modules/ui.py b/modules/ui.py
index f5564d0ef..b1a8c776d 100644
--- a/modules/ui.py
+++ b/modules/ui.py
@@ -323,7 +323,7 @@ def create_ui(txt2img, img2img, run_extras, run_pnginfo):
                 with gr.Group():
                     switch_mode = gr.Radio(label='Mode', elem_id="img2img_mode", choices=['Redraw whole image', 'Inpaint a part of image', 'Loopback', 'SD upscale'], value='Redraw whole image', type="index", show_label=False)
                     init_img = gr.Image(label="Image for img2img", source="upload", interactive=True, type="pil")
-                    init_img_with_mask = gr.Image(label="Image for inpainting with mask", elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", visible=False)
+                    init_img_with_mask = gr.Image(label="Image for inpainting with mask", elem_id="img2maskimg", source="upload", interactive=True, type="pil", tool="sketch", visible=False, image_mode="RGBA")
                     resize_mode = gr.Radio(label="Resize mode", show_label=False, choices=["Just resize", "Crop and resize", "Resize and fill"], type="index", value="Just resize")
 
                 steps = gr.Slider(minimum=1, maximum=150, step=1, label="Sampling Steps", value=20)
diff --git a/requirements.txt b/requirements.txt
index c9e3f2fce..ba1bc2815 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -10,5 +10,6 @@ omegaconf
 pytorch_lightning
 diffusers
 invisible-watermark
+scikit-image
 git+https://github.com/crowsonkb/k-diffusion.git
 git+https://github.com/TencentARC/GFPGAN.git
diff --git a/requirements_versions.txt b/requirements_versions.txt
index 177c6b58e..e8a7470cd 100644
--- a/requirements_versions.txt
+++ b/requirements_versions.txt
@@ -8,3 +8,4 @@ torch
 transformers==4.19.2
 omegaconf==2.1.1
 pytorch_lightning==1.7.2
+scikit-image==0.19.2
diff --git a/script.js b/script.js
index 51ace27fc..f2cd8877e 100644
--- a/script.js
+++ b/script.js
@@ -172,3 +172,19 @@ function submit(){
     }
     return res
 }
+
+window.addEventListener('paste', e => {
+    const files = e.clipboardData.files;
+    if (!files || files.length !== 1) {
+        return;
+    }
+    if (!['image/png', 'image/gif', 'image/jpeg'].includes(files[0].type)) {
+        return;
+    }
+    [...gradioApp().querySelectorAll('input[type=file][accept="image/x-png,image/gif,image/jpeg"]')]
+        .filter(input => !input.matches('.\\!hidden input[type=file]'))
+        .forEach(input => {
+            input.files = files;
+            input.dispatchEvent(new Event('change'))
+        });
+});
diff --git a/webui.bat b/webui.bat
index 055a19b04..0de2ab88d 100644
--- a/webui.bat
+++ b/webui.bat
@@ -35,7 +35,7 @@ echo Unable to create venv in directory %VENV_DIR%
 goto :show_stdout_stderr
 
 :activate_venv
-set PYTHON=%~dp0%VENV_DIR%\Scripts\Python.exe
+set PYTHON="%~dp0%VENV_DIR%\Scripts\Python.exe"
 %PYTHON% --version
 echo venv %PYTHON%
 goto :install_torch