reset p2p app

app_haircolor_pix2pix.py

@@ -11,10 +11,8 @@ from segment_utils import(
     restore_result,
 )
 from diffusers import (
-    DiffusionPipeline,
     StableDiffusionInstructPix2PixPipeline,
     EulerAncestralDiscreteScheduler,
-    T2IAdapter,
 )
 
 from controlnet_aux import (
@@ -28,25 +26,15 @@ BASE_MODEL = "timbrooks/instruct-pix2pix"
 
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
 
-DEFAULT_EDIT_PROMPT = "change hair to blue"
+DEFAULT_EDIT_PROMPT = "turn hair into blue"
 DEFAULT_NEGATIVE_PROMPT = "worst quality, normal quality, low quality, low res, blurry, text, watermark, logo, banner, extra digits, cropped, jpeg artifacts, signature, username, error, sketch ,duplicate, ugly, monochrome, horror, geometry, mutation, disgusting, poorly drawn face, bad face, fused face, ugly face, worst face, asymmetrical, unrealistic skin texture, bad proportions, out of frame, poorly drawn hands, cloned face, double face"
 
 DEFAULT_CATEGORY = "hair"
 
-canny_detector = CannyDetector()
-
-adapter = T2IAdapter.from_pretrained(
-    "TencentARC/t2iadapter_canny_sd15v2",
-    torch_dtype=torch.float16,
-    varient="fp16",
-)
-
-basepipeline = DiffusionPipeline.from_pretrained(
+basepipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
     BASE_MODEL,
     torch_dtype=torch.float16,
     use_safetensors=True,
-    adapter=adapter,
-    custom_pipeline="./pipelines/pipeline_sd_adapter_p2p.py",
 )
 
 basepipeline.scheduler = EulerAncestralDiscreteScheduler.from_config(basepipeline.scheduler.config)
@@ -64,30 +52,19 @@ def image_to_image(
     guidance_scale: float,
     image_guidance_scale: float,
     generate_size: int,
-    cond_scale1: float = 1.2,
 ):
     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)
-    canny_image = canny_image.convert("L")
-
-    cond_image = canny_image
-    cond_scale = cond_scale1
 
     generator = torch.Generator(device=DEVICE).manual_seed(seed)
     generated_image = basepipeline(
         generator=generator,
         prompt=edit_prompt,
-        negative_prompt=DEFAULT_NEGATIVE_PROMPT,
         image=input_image,
-        height=generate_size,
-        width=generate_size,
         guidance_scale=guidance_scale,
         image_guidance_scale=image_guidance_scale,
         num_inference_steps=num_steps,
-        adapter_image=cond_image,
-        adapter_conditioning_scale=cond_scale,
     ).images[0]
     
     run_task_time, time_cost_str = get_time_cost(run_task_time, time_cost_str)
@@ -122,7 +99,6 @@ def create_demo() -> gr.Blocks:
                     mask_dilation = gr.Slider(minimum=0, maximum=10, value=2, step=1, label="Mask Dilation")
                     seed = gr.Number(label="Seed", value=8)
                     category = gr.Textbox(label="Category", value=DEFAULT_CATEGORY, visible=False)
-                    cond_scale1 = gr.Slider(minimum=0, maximum=3, value=1.2, step=0.1, label="Cond_scale1")
                 g_btn = gr.Button("Edit Image")
                 
         with gr.Row():
@@ -141,7 +117,7 @@ def create_demo() -> gr.Blocks:
             outputs=[origin_area_image, croper],
         ).success(
             fn=image_to_image,
-            inputs=[origin_area_image, edit_prompt,seed, num_steps, guidance_scale, image_guidance_scale, generate_size, cond_scale1],
+            inputs=[origin_area_image, edit_prompt,seed, num_steps, guidance_scale, image_guidance_scale, generate_size],
             outputs=[generated_image, generated_cost],
         ).success(
             fn=restore_result,