Update app.py

Add function to include human pose in control tasks

app.py

@@ -45,6 +45,8 @@ def process(input_image, prompt, input_control, a_prompt, n_prompt, num_samples,
     # 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):
@@ -104,6 +106,42 @@ 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)
+
+
+        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)
+
+
+        samples, intermediates = ddim_sampler_pose.sample(ddim_steps, num_samples,
+                                                     shape, cond, verbose=False, eta=eta,
+                                                     unconditional_guidance_scale=scale,
+                                                     unconditional_conditioning=un_cond)
+
+
+        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"]
@@ -113,7 +151,8 @@ def create_canvas(w, h):
 block = gr.Blocks().queue()
 control_task_list = [
     "Canny Edge Map",
-    "Scribble"
+    "Scribble", 
+    "Pose"
 ]
 with block:
     gr.Markdown("## Adding Conditional Control to Text-to-Image Diffusion Models")