Update app.py

app.py

@@ -3,7 +3,7 @@ import numpy as np
 import PIL.Image
 from PIL import Image
 import random
-from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
+from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, StableDiffusionXLPipeline, AutoencoderKL
 from diffusers import DDIMScheduler, EulerAncestralDiscreteScheduler
 #from diffusers.utils import load_image
 
@@ -24,9 +24,14 @@ controlnet = ControlNetModel.from_pretrained(
 
 vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
 
-pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+#pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
+#    "yodayo-ai/holodayo-xl-2.1",
+#    controlnet=controlnet,
+#    vae=vae,
+#    torch_dtype=torch.float16,
+#)
+pipe = StableDiffusionXLPipeline.from_pretrained(
     "yodayo-ai/holodayo-xl-2.1",
-    controlnet=controlnet,
     vae=vae,
     torch_dtype=torch.float16,
 )
@@ -45,12 +50,12 @@ def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance
     use_image = False
     #image = None
     
-    if use_image :# and image is not None :
-        width, height = image['composite'].size
-        ratio = np.sqrt(1024. * 1024. / (width * height))
-        new_width, new_height = int(width * ratio), int(height * ratio)
-        image = image['composite'].resize((new_width, new_height))
-        print(image)
+    #if use_image :# and image is not None :
+    #    width, height = image['composite'].size
+    #    ratio = np.sqrt(1024. * 1024. / (width * height))
+    #    new_width, new_height = int(width * ratio), int(height * ratio)
+    #    image = image['composite'].resize((new_width, new_height))
+    #    print(image)
 
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
@@ -58,17 +63,17 @@ def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance
     generator = torch.Generator().manual_seed(seed)
 
     if use_image:
-        output_image = pipe(
-            prompt=prompt + ", masterpiece, best quality, very aesthetic, absurdres",
-            negative_prompt=negative_prompt,
-            image=image,
-            controlnet_conditioning_scale=1.0,
-            guidance_scale=guidance_scale,
-            num_inference_steps=num_inference_steps,
-            width=new_width,
-            height=new_height,
-            generator=generator
-        ).images[0]
+        #output_image = pipe(
+        #    prompt=prompt + ", masterpiece, best quality, very aesthetic, absurdres",
+        #    negative_prompt=negative_prompt,
+        #    image=image,
+        #    controlnet_conditioning_scale=1.0,
+        #    guidance_scale=guidance_scale,
+        #    num_inference_steps=num_inference_steps,
+        #    width=new_width,
+        #    height=new_height,
+        #    generator=generator
+        #).images[0]
     else:
         # If no valid image is provided, generate an image based only on the text prompt
         output_image = pipe(