Update README.md

README.md

@@ -68,12 +68,14 @@ Let's have a look at a simple example using the [Canny Adapter](https://huggingf
 ```py
 from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, EulerAncestralDiscreteScheduler, AutoencoderKL
 from diffusers.utils import load_image, make_image_grid
-from controlnet_aux.midas import MidasDetector
+from controlnet_aux import OpenposeDetector
 import torch
+import numpy as np
+from PIL import Image
 
 # load adapter
 adapter = T2IAdapter.from_pretrained(
-  "TencentARC/t2i-adapter-depth-midas-sdxl-1.0", torch_dtype=torch.float16, varient="fp16"
+  "TencentARC/t2i-adapter-openpose-sdxl-1.0", torch_dtype=torch.float16
 ).to("cuda")
 
 # load euler_a scheduler
@@ -85,24 +87,22 @@ pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
 ).to("cuda")
 pipe.enable_xformers_memory_efficient_attention()
 
-midas_depth = MidasDetector.from_pretrained(
-  "valhalla/t2iadapter-aux-models", filename="dpt_large_384.pt", model_type="dpt_large"
-).to("cuda")
+open_pose = OpenposeDetector.from_pretrained("lllyasviel/Annotators")
 ```
 
 - Condition Image
 ```py
-url = "https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_mid.jpg"
+url = "https://huggingface.co/Adapter/t2iadapter/resolve/main/people.jpg"
 image = load_image(url)
-image = midas_depth(
-  image, detect_resolution=512, image_resolution=1024
-)
+image = open_pose(image, detect_resolution=512, image_resolution=1024)
+image = np.array(image)[:, :, ::-1]           
+image = Image.fromarray(np.uint8(image)) 
 ```
-<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_depth_mid.png"><img width="480" style="margin:0;padding:0;" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_depth_mid.png"/></a>
+<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/openpose.png"><img width="480" style="margin:0;padding:0;" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/openpose.png"/></a>
 
 - Generation
 ```py
-prompt = "A photo of a room, 4k photo, highly detailed"
+prompt = "A couple, 4k photo, highly detailed"
 negative_prompt = "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured"
 
 gen_images = pipe(
@@ -113,9 +113,9 @@ gen_images = pipe(
   adapter_conditioning_scale=1,
   guidance_scale=7.5,  
 ).images[0]
-gen_images.save('out_mid.png')
+gen_images.save('out_pose.png')
 ```
-<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_depth_mid.png"><img width="480" style="margin:0;padding:0;" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_depth_mid.png"/></a>
+<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/res_pose.png"><img width="480" style="margin:0;padding:0;" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/res_pose.png"/></a>
 
 ### Training