Update app.py

app.py

@@ -20,6 +20,13 @@ canny_checkpoint = "models/control_sd15_canny.pth"
 scribble_checkpoint = "models/control_sd15_scribble.pth"
 pose_checkpoint = "models/control_sd15_openpose.pth"
 
+canny_model = create_model('./models/cldm_v15.yaml').cpu()
+canny_model.load_state_dict(load_state_dict(cached_download(
+    hf_hub_url(REPO_ID, canny_checkpoint)
+), location='cuda'))
+canny_model = canny_model.cuda()
+ddim_sampler = DDIMSampler(canny_model)
+
 pose_model = create_model('./models/cldm_v15.yaml').cpu()
 pose_model.load_state_dict(load_state_dict(cached_download(
     hf_hub_url(REPO_ID, pose_checkpoint)
@@ -38,8 +45,38 @@ 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)
-    else:
+    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)
+
+        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)
+
+        samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples,
+                                                     shape, cond, verbose=False, eta=eta,
+                                                     unconditional_guidance_scale=scale,
+                                                     unconditional_conditioning=un_cond)
+        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():
@@ -114,6 +151,7 @@ def create_canvas(w, h):
     
 block = gr.Blocks().queue()
 control_task_list = [
+    "Canny Edge Map"
     "Scribble", 
     "Pose"
 ]
@@ -135,6 +173,8 @@ with block:
             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)
+                low_threshold = gr.Slider(label="Canny low threshold", minimum=1, maximum=255, value=100, step=1)
+                high_threshold = gr.Slider(label="Canny high threshold", minimum=1, maximum=255, value=200, step=1)
                 ddim_steps = gr.Slider(label="Steps", minimum=1, maximum=100, value=20, step=1)
                 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)
@@ -144,9 +184,25 @@ with block:
                                       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]
+    ips = [input_image, prompt, input_control, a_prompt, n_prompt, num_samples, image_resolution, ddim_steps, scale, seed, eta, low_threshold, high_threshold]
     run_button.click(fn=process, inputs=ips, outputs=[result_gallery])
     examples_list = [
+                [
+            "bird.png", 
+            "bird",
+            "Canny Edge Map",
+            "best quality, extremely detailed",
+            'longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality',
+             1, 
+            512,
+            20, 
+            9.0, 
+            123490213,
+            0.0, 
+            100, 
+            200
+            
+        ],
         
                 [
             "turtle.png", 
@@ -159,7 +215,25 @@ with block:
             20, 
             9.0, 
             123490213,
-            0.0
+            0.0,
+            100,
+            200
+            
+        ]
+                  [
+            "pose1.png", 
+            "Chef in the Kitchen",
+            "Pose",
+            "best quality, extremely detailed",
+            'longbody, lowres, bad anatomy, bad hands, missing fingers, pubic hair,extra digit, fewer digits, cropped, worst quality, low quality',
+             1, 
+            512,
+            20, 
+            9.0, 
+            123490213,
+            0.0,
+            100,
+            200
             
         ]
     ]