Xintao williamberman commited on
Commit
9ac874b
1 Parent(s): 6fed013

update model card (#1)

Browse files

- update model card (94e2224660bb13d2ff7a51201ef909f0d4ec7a1d)


Co-authored-by: Will Berman <williamberman@users.noreply.huggingface.co>

README.md CHANGED
@@ -1,3 +1,92 @@
1
  ---
2
- duplicated_from: diffusers/t2iadapter_depth_sd14v1
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: runwayml/stable-diffusion-v1-5
4
+ tags:
5
+ - art
6
+ - t2i-adapter
7
+ - controlnet
8
+ - stable-diffusion
9
+ - image-to-image
10
  ---
11
+
12
+ # T2I Adapter - Depth
13
+
14
+ 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.
15
+
16
+ This checkpoint provides conditioning on depth for the stable diffusion 1.4 checkpoint.
17
+
18
+ ## Model Details
19
+ - **Developed by:** T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
20
+ - **Model type:** Diffusion-based text-to-image generation model
21
+ - **Language(s):** English
22
+ - **License:** Apache 2.0
23
+ - **Resources for more information:** [GitHub Repository](https://github.com/TencentARC/T2I-Adapter), [Paper](https://arxiv.org/abs/2302.08453).
24
+ - **Cite as:**
25
+
26
+ @misc{
27
+ title={T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models},
28
+ author={Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie},
29
+ year={2023},
30
+ eprint={2302.08453},
31
+ archivePrefix={arXiv},
32
+ primaryClass={cs.CV}
33
+ }
34
+
35
+ ### Checkpoints
36
+
37
+ | Model Name | Control Image Overview| Control Image Example | Generated Image Example |
38
+ |---|---|---|---|
39
+ |[TencentARC/t2iadapter_color_sd14v1](https://huggingface.co/TencentARC/t2iadapter_color_sd14v1)<br/> *Trained with spatial color palette* | A image with 8x8 color palette.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/color_sample_output.png"/></a>|
40
+ |[TencentARC/t2iadapter_canny_sd14v1](https://huggingface.co/TencentARC/t2iadapter_canny_sd14v1)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/canny_sample_output.png"/></a>|
41
+ |[TencentARC/t2iadapter_sketch_sd14v1](https://huggingface.co/TencentARC/t2iadapter_sketch_sd14v1)<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/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"><img width="64" style="margin:0;padding:0;" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/sketch_sample_output.png"/></a>|
42
+ |[TencentARC/t2iadapter_depth_sd14v1](https://huggingface.co/TencentARC/t2iadapter_depth_sd14v1)<br/> *Trained with Midas depth estimation* | A grayscale image with black representing deep areas and white representing shallow areas.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/depth_sample_output.png"/></a>|
43
+ |[TencentARC/t2iadapter_openpose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_openpose_sd14v1)<br/> *Trained with OpenPose bone image* | A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/openpose_sample_output.png"/></a>|
44
+ |[TencentARC/t2iadapter_keypose_sd14v1](https://huggingface.co/TencentARC/t2iadapter_keypose_sd14v1)<br/> *Trained with mmpose skeleton image* | A [mmpose skeleton](https://github.com/open-mmlab/mmpose) image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/keypose_sample_output.png"/></a>|
45
+ |[TencentARC/t2iadapter_seg_sd14v1](https://huggingface.co/TencentARC/t2iadapter_seg_sd14v1)<br/>*Trained with semantic segmentation* | An [custom](https://github.com/TencentARC/T2I-Adapter/discussions/25) segmentation protocol image.|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_input.png"/></a>|<a href="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"><img width="64" src="https://huggingface.co/datasets/diffusers/docs-images/resolve/main/t2i-adapter/seg_sample_output.png"/></a> |
46
+ |[TencentARC/t2iadapter_canny_sd15v2](https://huggingface.co/TencentARC/t2iadapter_canny_sd15v2)||
47
+ |[TencentARC/t2iadapter_depth_sd15v2](https://huggingface.co/TencentARC/t2iadapter_depth_sd15v2)||
48
+ |[TencentARC/t2iadapter_sketch_sd15v2](https://huggingface.co/TencentARC/t2iadapter_sketch_sd15v2)||
49
+ |[TencentARC/t2iadapter_zoedepth_sd15v1](https://huggingface.co/TencentARC/t2iadapter_zoedepth_sd15v1)||
50
+
51
+ ## Example
52
+
53
+ 1. Dependencies
54
+
55
+ ```sh
56
+ pip install diffusers transformers controlnet_aux
57
+ ```
58
+
59
+ 2. Run code:
60
+
61
+ ```python
62
+ from controlnet_aux import MidasDetector
63
+ from PIL import Image
64
+ from diffusers import T2IAdapter, StableDiffusionAdapterPipeline
65
+ import torch
66
+
67
+ midas = MidasDetector.from_pretrained("lllyasviel/Annotators")
68
+
69
+ image = Image.open('./images/depth_input.png')
70
+
71
+ image = midas(image)
72
+
73
+ image.save('./images/depth.png')
74
+
75
+ adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_depth_sd14v1", torch_dtype=torch.float16)
76
+ pipe = StableDiffusionAdapterPipeline.from_pretrained(
77
+ "CompVis/stable-diffusion-v1-4", adapter=adapter, safety_checker=None, torch_dtype=torch.float16, variant="fp16"
78
+ )
79
+
80
+ pipe.to('cuda')
81
+
82
+ generator = torch.Generator().manual_seed(1)
83
+
84
+ openpose_out = pipe(prompt="storm trooper giving a speech", image=image, generator=generator).images[0]
85
+
86
+ openpose_out.save('./images/depth_output.png')
87
+ ```
88
+
89
+
90
+ ![depth_input](./images/depth_input.png)
91
+ ![depth](./images/depth.png)
92
+ ![depth_output](./images/depth_output.png)
images/depth.png ADDED
images/depth_input.png ADDED
images/depth_output.png ADDED