Update pipeline.py

pipeline.py

@@ -60,8 +60,9 @@ EXAMPLE_DOC_STRING = """
         import torch
         from diffusers import DiffusionPipeline, FluxTransformer2DModel
         from transformers import T5EncoderModel
-        from diffusers.utils import load_image
+        from diffusers.utils import load_image, make_image_grid
         from image_gen_aux import DepthPreprocessor # https://github.com/huggingface/image_gen_aux
+        from PIL import Image
         import numpy as np
 
         pipe = DiffusionPipeline.from_pretrained(
@@ -81,27 +82,28 @@ EXAMPLE_DOC_STRING = """
         pipe.to("cuda")
 
         prompt = "The head of a human in a robot body giving a heated speech"
-        control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
+        image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
 
-        head_mask = np.ones_like(control_image)*255
+        head_mask = np.ones_like(image)*255
         head_mask[65:380,300:642] = 0
         mask_image = Image.fromarray(head_mask)
 
         processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
-        control_image = processor(control_image)[0].convert("RGB")
+        control_image = processor(image)[0].convert("RGB")
 
-        image = pipe(
+        output = pipe(
             prompt=prompt,
+            image=image,
             control_image=control_image,
             mask_image=mask_image,
-            strength=0.9,
             height=1024,
             width=1024,
             num_inference_steps=30,
+            strength=0.9,
             guidance_scale=10.0,
             generator=torch.Generator().manual_seed(42),
         ).images[0]
-        image.save("output.png")
+        make_image_grid([image, control_image, mask_image, output], rows=1, cols=4).save("output.png")
 
         ```
 """