Update README.md

README.md

@@ -1,3 +1,54 @@
 ---
-license: apache-2.0
+license: mit
+tags:
+- image-to-image
+datasets:
+- yulu2/InstructCV-Demo-Data
 ---
+
+# INSTRUCTCV: YOUR TEXT-TO-IMAGE MODEL IS SECRETLY A VISION GENERALIST
+
+GitHub: https://github.com
+
+[![pCVB5B8.png](https://s1.ax1x.com/2023/06/11/pCVB5B8.png)](https://imgse.com/i/pCVB5B8)
+
+
+## Example
+
+To use `InstructCV`, install `diffusers` using `main` for now. The pipeline will be available in the next release
+
+```bash
+pip install diffusers accelerate safetensors transformers
+```
+
+```python
+import PIL
+import requests
+import torch
+from diffusers import StableDiffusionInstructPix2PixPipeline, EulerAncestralDiscreteScheduler
+
+model_id = "yulu2/InstructCV"
+pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained(model_id, torch_dtype=torch.float16, safety_checker=None, variant="ema")
+pipe.to("cuda")
+pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+
+url = "https://raw.githubusercontent.com/timothybrooks/instruct-pix2pix/main/imgs/example.jpg"
+
+def download_image(url):
+    image = PIL.Image.open(requests.get(url, stream=True).raw)
+    image = PIL.ImageOps.exif_transpose(image)
+    image = image.convert("RGB")
+    return image
+
+image = download_image(URL)
+width, height = image.size
+factor = 512 / max(width, height)
+factor = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height)
+width = int((width * factor) // 64) * 64
+height = int((height * factor) // 64) * 64
+image = ImageOps.fit(image, (width, height), method=Image.Resampling.LANCZOS)
+
+prompt = "Detect the person."
+images = pipe(prompt, image=image, num_inference_steps=100).images
+images[0]
+```