test control img2img

app.py

@@ -1,6 +1,6 @@
 import gradio as gr
 
-from app_haircolor_refiner import create_demo as create_demo_haircolor
+from app_haircolor_img2img import create_demo as create_demo_haircolor
 
 with gr.Blocks(css="style.css") as demo:
     with gr.Tabs():

app_civitai.py

@@ -0,0 +1,6 @@
+import os
+
+from diffusers.pipelines.stable_diffusion.convert_from_ckpt import download_from_original_stable_diffusion_ckpt
+
+if not os.path.exists('juggernaut_aftermath-inpainting.safetensors'):
+    os.system("wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth -P .")

app_haircolor_img2img.py

@@ -10,7 +10,7 @@ from segment_utils import(
     restore_result,
 )
 from diffusers import (
-    StableDiffusionControlNetPipeline,
+    StableDiffusionControlNetImg2ImgPipeline,
     ControlNetModel,
     DDIMScheduler,
     DPMSolverMultistepScheduler,
@@ -45,16 +45,16 @@ hed_detector = hed_detector.to(DEVICE)
 
 controlnet = [
     ControlNetModel.from_pretrained(
-        "lllyasviel/control_v11e_sd15_ip2p", 
+        "lllyasviel/control_v11p_sd15_lineart", 
         torch_dtype=torch.float16,
     ),
     ControlNetModel.from_pretrained(
-        "lllyasviel/control_v11p_sd15_lineart", 
+        "lllyasviel/control_v11p_sd15_softedge", 
         torch_dtype=torch.float16,
     ),
 ]
 
-basepipeline = StableDiffusionControlNetPipeline.from_pretrained(
+basepipeline = StableDiffusionControlNetImg2ImgPipeline.from_pretrained(
     BASE_MODEL,
     torch_dtype=torch.float16,
     use_safetensors=True,
@@ -82,15 +82,18 @@ 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)
-    lineart_image = lineart_detector(input_image, 384, generate_size)
+    lineart_image = lineart_detector(input_image, 768, generate_size)
+
+    pidinet_image = pidiNet_detector(input_image, 768, generate_size)
 
-    cond_image = [input_image, lineart_image]
+    cond_image = [lineart_image, pidinet_image]
 
     generator = torch.Generator(device=DEVICE).manual_seed(seed)
     generated_image = basepipeline(
         generator=generator,
         prompt=edit_prompt,
-        image=cond_image,
+        image=input_image,
+        control_image=cond_image,
         height=generate_size,
         width=generate_size,
         guidance_scale=guidance_scale,