Added Function

.idea/workspace.xml

@@ -5,7 +5,7 @@
   </component>
   <component name="ChangeListManager">
     <list default="true" id="3cb50146-66c1-4999-864a-398a7d42ffa4" name="Changes" comment="">
-      <change afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/app.py" beforeDir="false" afterPath="$PROJECT_DIR$/app.py" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -46,7 +46,7 @@
       <option name="number" value="Default" />
       <option name="presentableId" value="Default" />
       <updated>1677222707113</updated>
-      <workItem from="1677222708286" duration="1445000" />
+      <workItem from="1677222708286" duration="2503000" />
     </task>
     <servers />
   </component>

app.py

@@ -42,54 +42,17 @@ ddim_sampler_scribble = DDIMSampler(scribble_model)
 
 save_memory = False
 
-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)
-    elif input_control == "Pose":
-        return process_pose(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, 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):
-    with torch.no_grad():
-        img = resize_image(HWC3(input_image), image_resolution)
-        H, W, C = img.shape
-
-        detected_map = apply_canny(img, low_threshold, high_threshold)
-        detected_map = HWC3(detected_map)
-
-        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()
-
-        seed_everything(seed)
-
-        if save_memory:
-            canny_model.low_vram_shift(is_diffusing=False)
+def process(input_image, prompt, input_control, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold):
+    # TODO: Clean Function for single Task
 
-        cond = {"c_concat": [control], "c_crossattn": [canny_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
-        un_cond = {"c_concat": [control], "c_crossattn": [canny_model.get_learned_conditioning([n_prompt] * num_samples)]}
-        shape = (4, H // 8, W // 8)
+    if input_control == "Scribble":
+        return process_scribble(input_image, prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta)
 
-        if save_memory:
-            canny_model.low_vram_shift(is_diffusing=False)
+def process_scribble(input_image, prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta):
 
-        samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples,
-                                                     shape, cond, verbose=False, eta=eta,
-                                                     unconditional_guidance_scale=scale,
-                                                     unconditional_conditioning=un_cond)
+    a_prompt = 'best quality, extremely detailed, architecture render, photorealistic, hyper realistic, surreal, dali, 3d rendering, render, 8k, 16k, extremely detailed, unreal engine, octane, maya'
+    n_prompt = 'longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality'
 
-        if save_memory:
-            canny_model.low_vram_shift(is_diffusing=False)
-            
-        x_samples = canny_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 process_scribble(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), image_resolution)
         H, W, C = img.shape
@@ -127,48 +90,6 @@ 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_pose(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, scale, seed, eta):
-    with torch.no_grad():
-        input_image = HWC3(input_image)
-        detected_map, _ = apply_openpose(resize_image(input_image, detect_resolution))
-        detected_map = HWC3(detected_map)
-        img = resize_image(input_image, image_resolution)
-        H, W, C = img.shape
-
-        detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_NEAREST)
-
-        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)
-
-        if save_memory:
-            pose_model.low_vram_shift(is_diffusing=False)
-
-    
-        cond = {"c_concat": [control], "c_crossattn": [pose_model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
-        un_cond = {"c_concat": [control], "c_crossattn": [pose_model.get_learned_conditioning([n_prompt] * num_samples)]}
-        shape = (4, H // 8, W // 8)
-
-        if save_memory:
-            pose_model.low_vram_shift(is_diffusing=False)
-            
-        samples, intermediates = ddim_sampler_pose.sample(ddim_steps, num_samples,
-                                                     shape, cond, verbose=False, eta=eta,
-                                                     unconditional_guidance_scale=scale,
-                                                     unconditional_conditioning=un_cond)
-
-        if save_memory:
-            pose_model.low_vram_shift(is_diffusing=False)
-            
-        x_samples = pose_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 [detected_map] + results
     
 def create_canvas(w, h):
     new_control_options = ["Interactive Scribble"]
@@ -191,8 +112,8 @@ with block:
     with gr.Row():
         with gr.Column():
             input_image = gr.Image(source='upload', type="numpy")
-            input_control = gr.Dropdown(control_task_list, value="Scribble", label="Control Task")
-            prompt = gr.Textbox(label="Prompt")
+            input_control = gr.Dropdown(control_task_list, value="Scribble", label="Task")
+            prompt = gr.Textbox(label="Architectural Style")
             run_button = gr.Button(label="Run")
             
             with gr.Accordion("Advanced options", open=False):
@@ -204,9 +125,7 @@ with block:
                 scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
                 seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
                 eta = gr.Slider(label="eta (DDIM)", minimum=0.0,maximum =1.0, value=0.0, step=0.1)
-                a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
-                n_prompt = gr.Textbox(label="Negative Prompt",
-                                      value='longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality')
+
         with gr.Column():
             result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery").style(grid=2, height='auto')
     ips = [input_image, prompt, input_control, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold]