Update app.py

Add new tab for interactive sketch

app.py

@@ -36,7 +36,9 @@ ddim_sampler_scribble = DDIMSampler(scribble_model)
 def process(input_image, prompt, input_control, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold):
     # TODO: Add other control tasks
     if input_control == "Scribble":
-        return process_scribble(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta) 
+        return process_scribble(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta)
+    elif input_control == "Interactive Scribble":
+        return process_scribble_interactive(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta)
     return process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold)
     
 def process_canny(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold):
@@ -96,11 +98,51 @@ def process_scribble(input_image, prompt, a_prompt, n_prompt, num_samples, image
 
         results = [x_samples[i] for i in range(num_samples)]
     return [255 - detected_map] + results
+
+def process_scribble_interactive(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta):
+    with torch.no_grad():
+        img = resize_image(HWC3(input_image['mask'][:, :, 0]), image_resolution)
+        H, W, C = img.shape
+
+        detected_map = np.zeros_like(img, dtype=np.uint8)
+        detected_map[np.min(img, axis=2) > 127] = 255
+
+        control = torch.from_numpy(detected_map.copy()).float().cuda() / 255.0
+        control = torch.stack([control for _ in range(num_samples)], dim=0)
+        control = einops.rearrange(control, 'b h w c -> b c h w').clone()
+
+        if seed == -1:
+            seed = random.randint(0, 65535)
+        seed_everything(seed)
+
+
+        cond = {"c_concat": [control], "c_crossattn": [scribble_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
+        un_cond = {"c_concat": [control], "c_crossattn": [scribble.get_learned_conditioning([n_prompt] * num_samples)]}
+        shape = (4, H // 8, W // 8)
+
+
+        samples, intermediates = ddim_sampler_scribble.sample(ddim_steps, num_samples,
+                                                     shape, cond, verbose=False, eta=eta,
+                                                     unconditional_guidance_scale=scale,
+                                                     unconditional_conditioning=un_cond)
+  
+        x_samples = scribble_model.decode_first_stage(samples)
+        x_samples = (einops.rearrange(x_samples, 'b c h w -> b h w c') * 127.5 + 127.5).cpu().numpy().clip(0, 255).astype(np.uint8)
+
+        results = [x_samples[i] for i in range(num_samples)]
+    return [255 - detected_map] + results
+
+    
+def create_canvas(w, h):
+    new_control_options = ["Interactive Scribble"]
+    return np.zeros(shape=(h, w, 3), dtype=np.uint8) + 255
+
     
 block = gr.Blocks().queue()
 control_task_list = [
     "Canny Edge Map",
-    "Scribble"
+    "Scribble",
+    "Interactive Scribble"
 ]
 with block:
     gr.Markdown("## Adding Conditional Control to Text-to-Image Diffusion Models")
@@ -111,10 +153,22 @@ with block:
               ''')
     with gr.Row():
         with gr.Column():
-            input_image = gr.Image(source='upload', type="numpy")
-            input_control = gr.Dropdown(control_task_list, value="Canny Edge Map", label="Control Task")
+            with gr.Tab("Upload"):
+                input_image = gr.Image(source='upload', type="numpy")
+                
+            with gr.Tab("Interactive Scribble"):
+                canvas_width = gr.Slider(label="Canvas Width", minimum=256, maximum=1024, value=512, step=1)
+                canvas_height = gr.Slider(label="Canvas Height", minimum=256, maximum=1024, value=512, step=1)
+                create_button = gr.Button(label="Start", value='Open drawing canvas!')
+                input_image = gr.Image(source='upload', type='numpy', tool='sketch')
+                gr.Markdown(value='Do not forget to change your brush width to make it thinner. (Gradio do not allow developers to set brush width so you need to do it manually.) '
+                                  'Just click on the small pencil icon in the upper right corner of the above block.')
+                create_button.click(fn=create_canvas, inputs=[canvas_width, canvas_height], outputs=[input_image])
+
+            input_control = gr.Dropdown(control_task_list, value="Scribble", label="Control Task")
             prompt = gr.Textbox(label="Prompt")
             run_button = gr.Button(label="Run")
+            
             with gr.Accordion("Advanced options", open=False):
                 num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
                 image_resolution = gr.Slider(label="Image Resolution", minimum=256, maximum=768, value=512, step=256)