testing canny for now only

app.py

@@ -1,16 +1,13 @@
-from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
-from diffusers import UniPCMultistepScheduler
+# from controlnet_aux import OpenposeDetector
+# from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
+# from diffusers import UniPCMultistepScheduler
 import gradio as gr
-import numpy as np
-import torch
+# import torch
 import base64
-import cv2
 from io import BytesIO
 from PIL import Image, ImageFilter
-
-# Constants
-low_threshold = 100
-high_threshold = 200
+import cv2
+import numpy as np
 
 canvas_html = '<pose-maker/>'
 load_js = """
@@ -35,24 +32,27 @@ async (canvas, prompt) => {
 }
 """
 
-# Models
-controlnet = ControlNetModel.from_pretrained(
-    "lllyasviel/sd-controlnet-canny", torch_dtype=torch.float16
-)
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
-)
-pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+# # Models
+# controlnet = ControlNetModel.from_pretrained(
+#     "lllyasviel/sd-controlnet-depth", torch_dtype=torch.float16
+# )
+# pipe = StableDiffusionControlNetPipeline.from_pretrained(
+#     "runwayml/stable-diffusion-v1-5", controlnet=controlnet, safety_checker=None, torch_dtype=torch.float16
+# )
+# pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+
+# # This command loads the individual model components on GPU on-demand. So, we don't
+# # need to explicitly call pipe.to("cuda").
+# pipe.enable_model_cpu_offload()
 
-# This command loads the individual model components on GPU on-demand. So, we don't
-# need to explicitly call pipe.to("cuda").
-pipe.enable_model_cpu_offload()
+# # xformers
+# pipe.enable_xformers_memory_efficient_attention()
 
-# xformers
-pipe.enable_xformers_memory_efficient_attention()
+# # Generator seed,
+# generator = torch.manual_seed(0)
 
-# Generator seed,
-generator = torch.manual_seed(0)
+low_threshold = 100
+high_threshold = 200
 
 def get_canny_filter(image):
     if not isinstance(image, np.ndarray):
@@ -70,19 +70,19 @@ def generate_images(canvas, prompt):
         image_data = base64.b64decode(base64_img.split(',')[1])
         input_img = Image.open(BytesIO(image_data)).convert(
             'RGB').resize((512, 512))
-        input_img = input_img.filter(ImageFilter.GaussianBlur(radius=5))
+        input_img = input_img.filter(ImageFilter.GaussianBlur(radius=2))
         input_img = get_canny_filter(input_img)
-        output = pipe(
-            f'{prompt}, best quality, extremely detailed',
-            input_img,
-            generator=generator,
-            num_images_per_prompt=2,
-            num_inference_steps=20,
-            negative_prompt="longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
-        )
-        all_outputs = [input_img]
-        for image in output.images:
-            all_outputs.append(image)
+        # output = pipe(
+        #     prompt,
+        #     input_img,
+        #     generator=generator,
+        #     num_images_per_prompt=3,
+        #     num_inference_steps=20,
+        # )
+        all_outputs = [input_img, input_img, input_img]
+        # all_outputs.append(input_img)
+        # for image in output.images:
+        #     all_outputs.append(image)
         return all_outputs
     except Exception as e:
         raise gr.Error(str(e))