Update README.md

README.md

@@ -33,13 +33,14 @@ text_encoder_2 = T5EncoderModel.from_pretrained(
 )
 pipe.transformer = transformer
 pipe.text_encoder_2 = text_encoder_2
+pipe.enable_model_cpu_offload()
 pipe.to("cuda")
 
-prompt = "The head of a human in a robot body giving a heated speech"
+prompt = "a blue robot singing opera with human-like expressions"
 image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
 
-head_mask = np.ones_like(image)*255
-head_mask[65:380,300:642] = 0
+head_mask = np.zeros_like(image)
+head_mask[65:580,300:642] = 255
 mask_image = Image.fromarray(head_mask)
 
 processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
@@ -50,14 +51,11 @@ output = pipe(
     image=image,
     control_image=control_image,
     mask_image=mask_image,
-    height=1024,
-    width=1024,
     num_inference_steps=30,
     strength=0.9,
-    guidance_scale=10.0,
+    guidance_scale=50.0,
     generator=torch.Generator().manual_seed(42),
 ).images[0]
-make_image_grid([image, control_image, mask_image, output], rows=1, cols=4).save("output.png")
-
+make_image_grid([image, control_image, mask_image, output.resize(image.size)], rows=1, cols=4).save("output.png")
 ```
-
+![](output.png)