change to app_haircolor_inpaint_15

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 
-from app_haircolor_inpaint_adapter_15 import create_demo as create_demo_haircolor
+from app_haircolor_inpaint_15 import create_demo as create_demo_haircolor
 
 with gr.Blocks(css="style.css") as demo:
     with gr.Tabs():

app_haircolor_inpaint_15.py

@@ -10,22 +10,12 @@ from segment_utils import(
     restore_result,
 )
 from diffusers import (
-    StableDiffusionControlNetInpaintPipeline,
-    ControlNetModel,
-    DDIMScheduler,
-    DPMSolverMultistepScheduler,
+    StableDiffusionInpaintPipeline,
     EulerAncestralDiscreteScheduler,
 )
 
-from controlnet_aux import (
-    CannyDetector,
-    LineartDetector,
-    PidiNetDetector,
-    HEDdetector,
-)
-
-BASE_MODEL = "stable-diffusion-v1-5/stable-diffusion-v1-5"
-# BASE_MODEL = "stable-diffusion-v1-5/stable-diffusion-inpainting"
+# BASE_MODEL = "stable-diffusion-v1-5/stable-diffusion-v1-5"
+BASE_MODEL = "stable-diffusion-v1-5/stable-diffusion-inpainting"
 # BASE_MODEL = "SG161222/Realistic_Vision_V2.0"
 
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
@@ -35,34 +25,12 @@ DEFAULT_NEGATIVE_PROMPT = "worst quality, normal quality, low quality, low res,
 
 DEFAULT_CATEGORY = "hair"
 
-canny_detector = CannyDetector()
-lineart_detector = LineartDetector.from_pretrained("lllyasviel/Annotators")
-lineart_detector = lineart_detector.to(DEVICE)
-
-pidiNet_detector = PidiNetDetector.from_pretrained('lllyasviel/Annotators')
-pidiNet_detector = pidiNet_detector.to(DEVICE)
-
-hed_detector = HEDdetector.from_pretrained('lllyasviel/Annotators')
-hed_detector = hed_detector.to(DEVICE)
-
-controlnet = [
-    ControlNetModel.from_pretrained(
-        "lllyasviel/control_v11e_sd15_ip2p",
-        torch_dtype=torch.float16,
-    ),
-    ControlNetModel.from_pretrained(
-        "lllyasviel/control_v11p_sd15_lineart", 
-        torch_dtype=torch.float16,
-    ),
-]
-
-basepipeline = StableDiffusionControlNetInpaintPipeline.from_pretrained(
+basepipeline = StableDiffusionInpaintPipeline.from_pretrained(
     BASE_MODEL,
     torch_dtype=torch.float16,
-    use_safetensors=True,
-    controlnet=controlnet,
+    # use_safetensors=True,
 )
-# basepipeline.scheduler = DDIMScheduler.from_config(basepipeline.scheduler.config)
+
 basepipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(basepipeline.scheduler.config)
 
 basepipeline = basepipeline.to(DEVICE)
@@ -84,11 +52,6 @@ def image_to_image(
     run_task_time = 0
     time_cost_str = ''
     run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
-    # canny_image = canny_detector(input_image, int(generate_size*1), generate_size)
-    lineart_image = lineart_detector(input_image, 384, generate_size)
-    run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
-    # pidiNet_image = pidiNet_detector(input_image, 512, generate_size)
-    control_image = [lineart_image, input_image]
 
     generator = torch.Generator(device=DEVICE).manual_seed(seed)
     generated_image = basepipeline(
@@ -97,12 +60,10 @@ def image_to_image(
         negative_prompt=DEFAULT_NEGATIVE_PROMPT,
         image=input_image,
         mask_image=mask_image,
-        control_image=control_image,
         height=generate_size,
         width=generate_size,
         guidance_scale=guidance_scale,
         num_inference_steps=num_steps,
-        controlnet_conditioning_scale=[cond_scale1, cond_scale2],
     ).images[0]
     
     run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)