Create app.py

app.py

@@ -0,0 +1,168 @@
+
+Hugging Face's logo Hugging Face
+
+Models
+Datasets
+Spaces
+Docs
+Pricing
+Log In
+Spaces:
+diffusers
+/
+controlnet-openpose
+App
+Files and versions
+Community
+controlnet-openpose
+/ app.py
+patrickvonplaten's picture
+patrickvonplaten
+HF staff
+Update app.py
+4564155
+9 days ago
+raw
+history
+blame
+contribute
+delete
+No virus
+1.96 kB
+from controlnet_aux import OpenposeDetector
+from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+from diffusers import UniPCMultistepScheduler
+import gradio as gr
+import torch
+from PIL import Image, ImageDraw, ImageFont
+import os 
+import cv2
+from PIL import Image
+import numpy as np
+from diffusers.utils import load_image
+import random
+
+# Constants
+low_threshold = 100
+high_threshold = 200
+
+# Models
+pose_model = OpenposeDetector.from_pretrained("lllyasviel/ControlNet")
+controlnet = ControlNetModel.from_pretrained(
+    "lllyasviel/sd-controlnet-openpose", torch_dtype=torch.float16
+)
+pipe = StableDiffusionControlNetPipeline.from_pretrained(
+    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
+)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+
+# This command loads the individual model components on GPU on-demand. So, we don't
+# need to explicitly call pipe.to("cuda").
+pipe.enable_model_cpu_offload()
+
+# xformers
+pipe.enable_xformers_memory_efficient_attention()
+
+# Generator seed,
+generator = torch.manual_seed(0)
+
+def get_pose(image):
+    return pose_model(image) 
+
+
+
+def generate_an_image_from_text(text, text_size_, width, lenght):
+  # Create a blank image
+  image = Image.new('RGB', (width, lenght), color = (255, 255, 255))
+
+  # Create a drawing object
+  draw = ImageDraw.Draw(image)
+
+  # font def 
+  font_dir = '/usr/share/fonts/truetype/liberation/'
+
+  # Get a list of all the font files in the directory
+  font_files = [os.path.join(font_dir, f) for f in os.listdir(font_dir) if os.path.isfile(os.path.join(font_dir, f))]
+  
+  # Select a random font
+  font_path = random.choice(font_files)
+  print(font_path)
+
+  font = ImageFont.truetype(font_path, text_size_)
+
+  # Get the text size
+  text_size = draw.textsize(text, font)
+
+  # Calculate the x and y positions for the text
+  x = (image.width - text_size[0]) / 2
+  y = (image.height - text_size[1]) / 2
+
+  # Draw the text on the image
+  draw.text((x, y), text, fill=(0, 0, 0), font=font)
+  return image
+
+def to_Canny(image):
+  # Let's load the popular vermeer image
+  image = np.array(image)
+
+  low_threshold = 100
+  high_threshold = 200
+
+  image = cv2.Canny(image, low_threshold, high_threshold)
+  image = image[:, :, None]
+  image = np.concatenate([image, image, image], axis=2)
+  canny_image = Image.fromarray(image)
+  return canny_image
+
+def inference(prompt,canny_image,number,seed ):
+  pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+  pipe.to("cuda")
+  #pipe.enable_model_cpu_offload()
+  pipe.enable_xformers_memory_efficient_attention()
+  generator = torch.manual_seed(seed)
+  
+  image_ = canny_image
+  prompt = prompt
+  out_image = pipe(
+      prompt, num_inference_steps=20, generator=generator, image=image_, num_images_per_prompt=number)
+  return out_image
+    
+def generate_images(image, prompt):
+    pose = get_pose(image)
+    output = pipe(
+        prompt,
+        pose,
+        generator=generator,
+        num_images_per_prompt=3,
+        num_inference_steps=20,
+    )
+    all_outputs = []
+    all_outputs.append(pose)
+    for image in output.images:
+        all_outputs.append(image)
+    return all_outputs
+
+def generation(prompt,text,seed,police_size, lenght, width,number):
+    img = generate_an_image_from_text(text,police_size,lenght,width)
+    img = to_Canny(img)
+    output = inference(prompt,img, number,seed)
+    all_outputs = []
+    for image in output.images:
+        all_outputs.append(image)
+    return all_outputs
+
+gr.Interface(fn=generation, 
+             inputs=["text", 
+                     "text",
+                     gr.Slider(0, 200),
+                     gr.Slider(0, 200),
+                     gr.Slider(0, 1024),
+                     gr.Slider(0, 1024),
+                     gr.Slider(0, 7)], 
+            outputs=gr.Gallery().style(grid=[2], height="auto")),
+            title="Generate a logo using Text ",
+            examples=[["A steampunk Alphabetic Logo, steampunk style, with glowing mecha parts, mecha alphabets, high quality, high res, ultra HD", "Logo",60,90,512,512,2]],
+            ).launch(enable_queue=True)
+
+
+