Update app.py

app.py

@@ -19,64 +19,22 @@ from PIL import Image
 # os.environ["no_proxy"] = "localhost,127.0.0.1,::1"
 device = "cuda:0"
 
-apply_uniformer = UniformerDetector()
-
 model = create_model('./models/cldm_v15.yaml').cpu()
-
-controlnet_path = "./models/sks_crack500_epoch_19.ckpt"
+sd_model_path = "/home/leiqin/stable-diffusion-webui/models/Stable-diffusion/sks_crack_ppl.ckpt"
+controlnet_path = "/home/leiqin/stable-diffusion-webui/extensions/sd-webui-controlnet/models/sks_crack_controlnet.pth"
+model.load_state_dict(load_state_dict(sd_model_path, location='cpu'), strict = False)
 model.load_state_dict(load_state_dict(controlnet_path, location='cpu'), strict = False)
 
 model = model.cuda()
 ddim_sampler = DDIMSampler(model)
+init_mask = Image.open("379.png").convert("L")
 
 
-def process(input_image, prompt, a_prompt, n_prompt, num_samples, image_resolution, detect_resolution, ddim_steps, guess_mode, strength, scale, seed, eta):
-    with torch.no_grad():
-        input_image = HWC3(input_image)
-        detected_map = apply_uniformer(resize_image(input_image, detect_resolution))
-        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 config.save_memory:
-            model.low_vram_shift(is_diffusing=False)
-
-        cond = {"c_concat": [control], "c_crossattn": [model.get_learned_conditioning([prompt + ', ' + a_prompt] * num_samples)]}
-        un_cond = {"c_concat": None if guess_mode else [control], "c_crossattn": [model.get_learned_conditioning([n_prompt] * num_samples)]}
-        shape = (4, H // 8, W // 8)
-
-        if config.save_memory:
-            model.low_vram_shift(is_diffusing=True)
-
-        model.control_scales = [strength * (0.825 ** float(12 - i)) for i in range(13)] if guess_mode else ([strength] * 13)  # Magic number. IDK why. Perhaps because 0.825**12<0.01 but 0.826**12>0.01
-        samples, intermediates = ddim_sampler.sample(ddim_steps, num_samples,
-                                                     shape, cond, verbose=False, eta=eta,
-                                                     unconditional_guidance_scale=scale,
-                                                     unconditional_conditioning=un_cond)
-
-        if config.save_memory:
-            model.low_vram_shift(is_diffusing=False)
-
-        x_samples = 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 model_sample(mask,
                 prompt = "sks crack, pavement cracks, HDR, Asphalt road, mudded",
                 a_prompt="", 
                 n_prompt="", 
-                num_samples=1, ddim_steps=50, guess_mode=False, strength=1.0, scale=7.0, seed=-1, eta=1.0):
+                num_samples=1, ddim_steps=50, guess_mode=False, strength=1.0, scale=7.0, seed=-1, eta=0.0):
     # mask --- numpy
     ddim_sampler = DDIMSampler(model)
 
@@ -120,13 +78,13 @@ with block:
         with gr.Column():
             with gr.Row():
                 with gr.Tabs(elem_id="mode_img2img"):
-                    with gr.TabItem('img2img', id='img2img', elem_id="img2img_img2img_tab") as tab_img2img:
-                        init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="numpy", tool="editor", image_mode="L").style(height=480)
+                    with gr.TabItem('txt2img', id='img2img', elem_id="img2img_img2img_tab") as tab_img2img:
+                        init_img = gr.Image(label="Image for img2img", elem_id="img2img_image", show_label=False, source="upload", interactive=True, type="numpy", tool="editor", image_mode="L", value=init_mask).style(height=480)
                         init_run_button = gr.Button(label="Run Init")
                     with gr.TabItem('Sketch', id='img2img_sketch', elem_id="img2img_img2img_sketch_tab") as tab_sketch:
                         sketch_img = gr.Image(label="Image for img2img", elem_id="img2img_sketch", show_label=False, source="canvas", interactive=True, type="numpy", tool="color-sketch", image_mode="L").style(height=480)
                         sketch_run_button = gr.Button(label="Run Sketch")
-                    prompt = gr.Textbox(label="Prompt")
+                    prompt = gr.Textbox(label="Prompt", value="sks crack")
             with gr.Row():
                 with gr.Accordion("Advanced options", open=False):
                     num_samples = gr.Slider(label="Images", minimum=1, maximum=12, value=1, step=1)
@@ -135,18 +93,18 @@ with block:
                     guess_mode = gr.Checkbox(label='Guess Mode', value=False)
                     detect_resolution = gr.Slider(label="Segmentation Resolution", minimum=128, maximum=1024, value=512, 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)
+                    scale = gr.Slider(label="Guidance Scale", minimum=0.1, maximum=30.0, value=7.0, step=0.1)
                     seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
                     eta = gr.Number(label="eta (DDIM)", value=0.0)
-                    a_prompt = gr.Textbox(label="Added Prompt", value='best quality, extremely detailed')
+                    a_prompt = gr.Textbox(label="Added Prompt", value='')
                     n_prompt = gr.Textbox(label="Negative Prompt",
-                                            value='longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality')
+                                            value='')
         with gr.Column():
             result_gallery = gr.Gallery(label='Output', show_label=False, elem_id="gallery").style(grid=2, height='auto')
-
+ 
     init_ips = [init_img, prompt, a_prompt, n_prompt, num_samples, ddim_steps, guess_mode, strength, scale, seed, eta]
     sketch_ips = [sketch_img, prompt, a_prompt, n_prompt, num_samples, ddim_steps, guess_mode, strength, scale, seed, eta]
     init_run_button.click(fn=model_sample, inputs=init_ips, outputs=[result_gallery])
     sketch_run_button.click(fn=model_sample, inputs=sketch_ips, outputs=[result_gallery])
 
-block.launch(server_name='0.0.0.0', server_port=3001)
+block.launch(server_name='0.0.0.0', server_port=6667, share=True)