Update README.md

README.md

@@ -3,7 +3,7 @@ license: mit
 tags:
 - image-to-image
 ---
-# ip2p-RoboPredict: InstructPix2Pix Fine-tuning for Robotic Action Frame Prediction
+# Action2Vision: InstructPix2Pix Fine-tuning for Robotic Action Frame Prediction
 GitHub: https://github.com/yutengzhang03/Action2Vision
 <img src='img/show-example.png'/>
 
@@ -22,18 +22,24 @@ import PIL
 import requests
 import torch
 from diffusers import StableDiffusionInstructPix2PixPipeline, EulerAncestralDiscreteScheduler
+
 model_id = "yutengz/Action2Vision"
 pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16, safety_checker=None)
 pipe.to("cuda")
 pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
-url = "https://github.com/yutengzhang03/Action2Vision/blob/main/img/source.png"
+
+
+to_tensor = transforms.ToTensor()
+resize = transforms.Resize((256, 256))
+
 def download_image(url):
-    image = PIL.Image.open(requests.get(url, stream=True).raw)
-    image = PIL.ImageOps.exif_transpose(image)
-    image = image.convert("RGB")
+    def download_image(url):
+    image = PIL.Image.open(requests.get(url, stream=True).raw).convert("RGB").resize((256, 256))
     return image
+
+url = "https://github.com/yutengzhang03/Action2Vision/blob/main/img/source.png"
 image = download_image(url)
 prompt = "There is a hammer and a block in the middle of the table. If the block is closer to the left robotic arm, it uses the left arm to pick up the hammer and strike the block; otherwise, it does the opposite."
-images = pipe(prompt, image=image, num_inference_steps=10, image_guidance_scale=1).images
+images = pipe(prompt, image=image).images
 images[0]
 ```