Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 
 T2I Adapter is a network providing additional conditioning to stable diffusion. Each t2i checkpoint takes a different type of conditioning as input and is used with a specific base stable diffusion checkpoint.
 
-This checkpoint provides conditioning on canny for the StableDiffusionXL checkpoint.
+This checkpoint provides conditioning on depth for the StableDiffusionXL checkpoint.
 
 ## Model Details
 - **Developed by:** T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
@@ -31,14 +31,17 @@ This checkpoint provides conditioning on canny for the StableDiffusionXL checkpo
     primaryClass={cs.CV}
   }
 
+
 ### Checkpoints
 
 | Model Name | Control Image Overview| Control Image Example | Generated Image Example |
 |---|---|---|---|
-|[Adapter/t2iadapter_canny_sdxlv1](https://huggingface.co/Adapter/t2iadapter_canny_sdxlv1)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href=""><img width="64" style="margin:0;padding:0;" src=""/></a>|<a href=""><img width="64" src=""/></a>|
-|[Adapter/t2iadapter_sketch_sdxlv1](https://huggingface.co/Adapter/t2iadapter_sketch_sdxlv1)<br/> *Trained with [PidiNet](https://github.com/zhuoinoulu/pidinet) edge detection* | A hand-drawn monochrome image with white outlines on a black background.|<a href=""><img width="64" style="margin:0;padding:0;" src=""/></a>|<a href=""><img width="64" src=""/></a>|
-|[Adapter/t2iadapter_depth_sdxlv1](https://huggingface.co/Adapter/t2iadapter_depth_sdxlv1)<br/> *Trained with Midas depth estimation*  | A grayscale image with black representing deep areas and white representing shallow areas.|<a href=""><img width="64" src=""/></a>|<a href=""><img width="64" src=""/></a>|
-|[Adapter/t2iadapter_openpose_sdxlv1](https://huggingface.co/Adapter/t2iadapter_openpose_sdxlv1)<br/> *Trained with OpenPose bone image*  | A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href=""><img width="64" src=""/></a>|<a href=""><img width="64" src=""/></a>|
+|[TencentARC/t2i-adapter-canny-sdxl-1.0](https://huggingface.co/TencentARC/t2i-adapter-canny-sdxl-1.0)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_canny.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_canny.png"/></a>|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_canny.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_canny.png"/></a>|
+|[TencentARC/t2i-adapter-sketch-sdxl-1.0](https://huggingface.co/TencentARC/t2i-adapter-sketch-sdxl-1.0)<br/> *Trained with [PidiNet](https://github.com/zhuoinoulu/pidinet) edge detection* | A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_sketch.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_sketch.png"/></a>|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_sketch.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_sketch.png"/></a>|
+|[TencentARC/t2i-adapter-lineart-sdxl-1.0](https://huggingface.co/TencentARC/t2i-adapter-lineart-sdxl-1.0)<br/> *Trained with lineart edge detection* | A hand-drawn monochrome image with white outlines on a black background.|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_lin.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_lin.png"/></a>|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_lin.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_lin.png"/></a>|
+|[TencentARC/t2i-adapter-depth-midas-sdxl-1.0](https://huggingface.co/TencentARC/t2i-adapter-depth-midas-sdxl-1.0)<br/> *Trained with Midas depth estimation*  | A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_depth_mid.png"><img width="64" 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/figs_SDXLV1.0/res_depth_mid.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_depth_mid.png"/></a>|
+|[TencentARC/t2i-adapter-depth-zoe-sdxl-1.0](https://huggingface.co/TencentARC/t2i-adapter-depth-zoe-sdxl-1.0)<br/> *Trained with Zoe depth estimation*  | A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_depth_zeo.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/cond_depth_zeo.png"/></a>|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_depth_zeo.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/res_depth_zeo.png"/></a>|
+|[Adapter/t2iadapter_openpose_sdxlv1](https://huggingface.co/Adapter/t2iadapter_openpose_sdxlv1)<br/> *Trained with OpenPose bone image*  | A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/openpose.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/openpose.png"/></a>|<a href="https://huggingface.co/Adapter/t2iadapter/resolve/main/res_pose.png"><img width="64" src="https://huggingface.co/Adapter/t2iadapter/resolve/main/res_pose.png"/></a>|
 
 
 ## Example
@@ -54,42 +57,47 @@ pip install transformers accelerate safetensors
 1. Images are first downloaded into the appropriate *control image* format.
  2. The *control image* and *prompt* are passed to the [`StableDiffusionXLAdapterPipeline`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py#L125).
 
-Let's have a look at a simple example using the [Canny Adapter](https://huggingface.co/Adapter/t2iadapter_canny_sdxlv1).
+Let's have a look at a simple example using the [Canny Adapter](https://huggingface.co/TencentARC/t2i-adapter-lineart-sdxl-1.0).
 
+- Dependency
 ```py
-from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, EulerAncestralDiscreteScheduler
+from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, EulerAncestralDiscreteScheduler, AutoencoderKL
 from diffusers.utils import load_image, make_image_grid
-from controlnet_aux.zoe import MidasDetector
+from controlnet_aux.midas import MidasDetector
+import torch
 
 # load adapter
 adapter = T2IAdapter.from_pretrained(
-  "Adapter/t2i-adapter-depth-midas-sdxl-1.0", torch_dtype=torch.float16, varient="fp16"
+  "TencentARC/t2i-adapter-depth-midas-sdxl-1.0", torch_dtype=torch.float16, varient="fp16"
 ).to("cuda")
 
 # load euler_a scheduler
 model_id = 'stabilityai/stable-diffusion-xl-base-1.0'
 euler_a = EulerAncestralDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
-vae= AutoencoderKL.from_pretrained(
-  "madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16
-)
+vae=AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
 pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
-  model_id, vae=vae, adapter=adapter, scheduler=euler_a, torch_dtype=torch.float16, variant="fp16", 
+    model_id, vae=vae, adapter=adapter, scheduler=euler_a, torch_dtype=torch.float16, variant="fp16", 
 ).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")
+```
 
-
-url = "https://raw.githubusercontent.com/lllyasviel/ControlNet/main/test_imgs/cyber.png"
+- Condition Image
+```py
+url = "https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_mid.jpg"
 image = load_image(url)
 image = midas_depth(
   image, detect_resolution=512, image_resolution=1024
-).resize((896, 1152))
+)
+```
+<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>
 
-prompt = "a robot, mount fuji in the background, 4k photo, highly detailed"
+- Generation
+```py
+prompt = "A photo of a room, 4k photo, highly detailed"
 negative_prompt = "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured"
 
 gen_images = pipe(
@@ -97,8 +105,9 @@ gen_images = pipe(
   negative_prompt=negative_prompt,
   image=image,
   num_inference_steps=30,
-  adapter_conditioning_scale=1, 
-  cond_tau=1
-).images
-gen_images[0]
-```
+  adapter_conditioning_scale=1,
+  guidance_scale=7.5,  
+).images[0]
+gen_images.save('out_mid.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>