Upload app.py

app.py

@@ -0,0 +1,88 @@
+import gradio as gr
+from src.process import *
+
+THEME=gr.themes.Default(font=[gr.themes.GoogleFont("IBM Plex Mono"), "ui-monospace","monospace"],
+                                           primary_hue="lime",
+                                           secondary_hue="emerald",
+                                           neutral_hue="stone",
+                                           )
+
+def create_demo():
+    
+    with gr.Blocks(theme=THEME) as demo:
+
+        gr.Markdown('# 🎭 theaTRON')
+        gr.Markdown('<img src="file/data/image-only.png">')
+        gr.Markdown('Type what you want to see and the app will create images with the faces in the input while preserving body pose. Should work for multiple humans too!')
+
+        prompt = gr.Textbox(value="Astronauts, photograph inside the ISS International Space Station corridor", label="Prompt:")
+        n_prompt = gr.Textbox(value="", label="Negative Prompt: Avoid these features in the image...")
+            
+        with gr.Group():
+            with gr.Box():
+                with gr.Column():
+                    with gr.Row() as main_blocks:
+                        with gr.Column() as input_step:
+                            gr.Markdown('# Input') 
+                            with gr.Tab("Upload Image"):
+                              image_upload = gr.Image(source='upload',
+                                                      height=500,
+                                                      type='pil',#numpy',
+                                                      tool=None,
+                                                      elem_classes="image_upload",
+                                                      label='Image Upload')
+                            with gr.Tab("Webcam"):
+                                image_cam = gr.Image(source='webcam',
+                                                   height=500,
+                                                   type='pil',#numpy',
+                                                   tool=None,
+                                                   elem_classes="image_upload",
+                                                   label='Webcam')
+                            send_button = gr.Button(label='Generate', value='Generate') 
+                            
+                        with gr.Column() as output_step:  
+                            gr.Markdown('# Output')   
+                            output_image = gr.Gallery(label="Generated images",
+                                                      show_label=False,
+                                                      preview=True,
+                                                      elem_id="output_image",
+                                                      object_fit="contain",
+                                                      height="auto")              
+            with gr.Accordion('Settings', open=False):
+                num_steps = gr.Slider(label='Steps',
+                                  minimum=1,
+                                  maximum=100,
+                                  value=25,
+                                  step=1)
+                original_resolution=gr.Checkbox(value=False,
+                                                label="Preserve Resolution",
+                                                info="Prevent Downscaling to 512 pixels (default)")
+                seed = gr.Slider(label='Seed',
+                                  minimum=-1,
+                                  maximum=2147483647,
+                                  step=1,
+                                  randomize=True)  
+                    
+
+        with gr.Accordion('How does it work?', open=False):
+            gr.Markdown('This demo was created by Mikolaj Czerkawski [@mikonvergence](https://twitter.com/mikonvergence) based on several 🌱 open-source tools. It only puts together existing models, so in some sense, nothing new here!')
+            gr.Markdown('## Pipeline Details')
+            gr.Markdown('### Step 1: Face Detection')
+            gr.Markdown('I use the model from kornia for face detection, since at the time of release, Segment Anything does not yet work with text prompts. Thank you, kornia team! https://kornia.readthedocs.io/en/latest/applications/face_detection.html')
+            gr.Markdown('### Step 2: Segment Anything')
+            gr.Markdown('I use Segment Anything from Meta (via HF transformers library) to segment the face based on the detection points. https://huggingface.co/docs/transformers/main/model_doc/sam')
+            gr.Markdown('### Step 3: Mask Post-processing')
+            gr.Markdown('The mask is blurred to achieve a smoother blend when recomposing the photo. Also, if a separate mask is used for the top of the head and the face, then the potential space between the two masks is morphologically filled.')
+            gr.Markdown('### Step 4: ControlNetInpaint')
+            gr.Markdown('Finally, the resulting mask is used with the ControlNetInpaint tool [ControlNetInpaint](https://github.com/mikonvergence/ControlNetInpaint) and the pose guide.')
+            gr.Markdown('---')
+            gr.Markdown('# Learn More About Diffusion 💡')
+            gr.Markdown('Check out my open-source ⏩[DiffusionFastForward](https://github.com/mikonvergence/DiffusionFastForward) course. It contains example code, executable notebooks, videos, notes, and a few use cases for training from scratch!')
+        
+        send_button.click(fn=forward, inputs=[image_cam, image_upload, prompt, n_prompt, num_steps, seed, original_resolution], outputs=[output_image])   
+        return demo
+
+if __name__ == "__main__":
+    demo = create_demo()
+    demo.launch(debug=True,
+                share=True)