Image Guidance Scale

app.py

@@ -10,7 +10,7 @@ import time
 import math
 import random
 import imageio
-from PIL import (Image, ImageFilter)
+from PIL import Image, ImageFilter
 import torch
 
 max_64_bit_int = 2**63 - 1
@@ -29,6 +29,7 @@ def check(
     denoising_steps,
     num_inference_steps,
     guidance_scale,
+    image_guidance_scale,
     randomize_seed,
     seed,
     progress = gr.Progress()):
@@ -45,6 +46,7 @@ def pix2pix(
     denoising_steps,
     num_inference_steps,
     guidance_scale,
+    image_guidance_scale,
     randomize_seed,
     seed,
     progress = gr.Progress()):
@@ -55,6 +57,7 @@ def pix2pix(
         denoising_steps,
         num_inference_steps,
         guidance_scale,
+        image_guidance_scale,
         randomize_seed,
         seed
     )
@@ -73,6 +76,9 @@ def pix2pix(
     if guidance_scale is None:
         guidance_scale = 5
 
+    if image_guidance_scale is None:
+        image_guidance_scale = 1.5
+
     if randomize_seed:
         seed = random.randint(0, max_64_bit_int)
 
@@ -90,7 +96,9 @@ def pix2pix(
     except:
         raise gr.Error("Can't open input image. You can try to first save your image in another format (.webp, .png, .jpeg, .bmp...).")
 
-    output_height, output_width, dummy_channel = np.array(input_image).shape
+    original_height, original_width, dummy_channel = np.array(input_image).shape
+    output_width = original_width
+    output_height = original_height
     mask_image = Image.new(mode = input_image.mode, size = (output_width, output_height), color = "white")
 
     limitation = "";
@@ -101,7 +109,7 @@ def pix2pix(
         output_width = math.floor(output_width * factor)
         output_height = math.floor(output_height * factor)
 
-        limitation = " Due to technical limitation, the image have been downscaled.";
+        limitation = " Due to technical limitation, the image have been downscaled and then upscaled.";
 
     # Width and height must be multiple of 8
     output_width = output_width - (output_width % 8)
@@ -118,10 +126,14 @@ def pix2pix(
         mask_image = mask_image,
         num_inference_steps = num_inference_steps,
         guidance_scale = guidance_scale,
+        image_guidance_scale = image_guidance_scale,
         denoising_steps = denoising_steps,
         show_progress_bar = True
     ).images[0]
 
+    if limitation != "":
+        output_image = output_image.resize((original_width, original_height))
+
     end = time.time()
     secondes = int(end - start)
     minutes = secondes // 60
@@ -164,8 +176,9 @@ with gr.Blocks() as interface:
         with gr.Accordion("Advanced options", open = False):
             negative_prompt = gr.Textbox(label = 'Negative prompt', placeholder = 'Describe what you do NOT want to see in the image', value = 'Watermark')
             denoising_steps = gr.Slider(minimum = 0, maximum = 1000, value = 0, step = 1, label = "Denoising", info = "lower=irrelevant result, higher=relevant result")
-            num_inference_steps = gr.Slider(minimum = 10, maximum = 25, value = 20, step = 1, label = "Number of inference steps", info = "lower=faster, higher=image quality")
+            num_inference_steps = gr.Slider(minimum = 10, maximum = 500, value = 20, step = 1, label = "Number of inference steps", info = "lower=faster, higher=image quality")
             guidance_scale = gr.Slider(minimum = 1, maximum = 13, value = 5, step = 0.1, label = "Classifier-Free Guidance Scale", info = "lower=image quality, higher=follow the prompt")
+            image_guidance_scale = gr.Slider(minimum = 1, value = 1.5, step = 0.1, label = "Image Guidance Scale", info = "lower=image quality, higher=follow the image")
             randomize_seed = gr.Checkbox(label = "\U0001F3B2 Randomize seed (not working, always checked)", value = True, info = "If checked, result is always different")
             seed = gr.Slider(minimum = 0, maximum = max_64_bit_int, step = 1, randomize = True, label = "Seed (if not randomized)")
 
@@ -181,6 +194,7 @@ with gr.Blocks() as interface:
         denoising_steps,
         num_inference_steps,
         guidance_scale,
+        image_guidance_scale,
         randomize_seed,
         seed
     ], outputs = [], queue = False, show_progress = False).success(pix2pix, inputs = [
@@ -190,6 +204,7 @@ with gr.Blocks() as interface:
         denoising_steps,
         num_inference_steps,
         guidance_scale,
+        image_guidance_scale,
         randomize_seed,
         seed
     ], outputs = [
@@ -205,6 +220,7 @@ with gr.Blocks() as interface:
             denoising_steps,
             num_inference_steps,
             guidance_scale,
+            image_guidance_scale,
             randomize_seed,
             seed
         ],
@@ -220,6 +236,7 @@ with gr.Blocks() as interface:
                     1,
                     20,
                     5,
+                    1.5,
                     True,
                     42
                 ],
@@ -230,6 +247,7 @@ with gr.Blocks() as interface:
                     1,
                     20,
                     5,
+                    1.5,
                     True,
                     42
                 ],
@@ -240,6 +258,7 @@ with gr.Blocks() as interface:
                     1,
                     20,
                     5,
+                    1.5,
                     True,
                     42
                 ],