T2I Adapter - Depth
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 depth for the stable diffusion 1.5 checkpoint.
Model Details
Developed by: T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models
Model type: Diffusion-based text-to-image generation model
Language(s): English
License: Apache 2.0
Resources for more information: GitHub Repository, Paper.
Cite as:
@misc{ title={T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models}, author={Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, Ying Shan, Xiaohu Qie}, year={2023}, eprint={2302.08453}, archivePrefix={arXiv}, primaryClass={cs.CV} }
Checkpoints
| Model Name | Control Image Overview | Control Image Example | Generated Image Example |
|---|---|---|---|
| TencentARC/t2iadaptercolorsd14v1 Trained with spatial color palette |
A image with 8x8 color palette. | ||
| TencentARC/t2iadaptercannysd14v1 Trained with canny edge detection |
A monochrome image with white edges on a black background. | ||
| TencentARC/t2iadaptersketchsd14v1 Trained with PidiNet edge detection |
A hand-drawn monochrome image with white outlines on a black background. | ||
| TencentARC/t2iadapterdepthsd14v1 Trained with Midas depth estimation |
A grayscale image with black representing deep areas and white representing shallow areas. | ||
| TencentARC/t2iadapteropenposesd14v1 Trained with OpenPose bone image |
A OpenPose bone image. | ||
| TencentARC/t2iadapterkeyposesd14v1 Trained with mmpose skeleton image |
A mmpose skeleton image. | ||
| TencentARC/t2iadaptersegsd14v1 Trained with semantic segmentation |
An custom segmentation protocol image. | ||
| TencentARC/t2iadaptercannysd15v2 | |||
| TencentARC/t2iadapterdepthsd15v2 | |||
| TencentARC/t2iadaptersketchsd15v2 | |||
| TencentARC/t2iadapterzoedepthsd15v1 |
Example
- Dependencies
pip install diffusers transformers controlnet_aux
- Run code:
from controlnet_aux import MidasDetector
from PIL import Image
from diffusers import T2IAdapter, StableDiffusionAdapterPipeline
import torch
midas = MidasDetector.from_pretrained("lllyasviel/Annotators")
image = Image.open('./images/depth_input.png')
image = midas(image)
image.save('./images/depth.png')
adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_depth_sd15v2", torch_dtype=torch.float16)
pipe = StableDiffusionAdapterPipeline.from_pretrained(
"runwayml/stable-diffusion-v1-5", adapter=adapter, safety_checker=None, torch_dtype=torch.float16, variant="fp16"
)
pipe.to('cuda')
generator = torch.Generator().manual_seed(1)
depth_out = pipe(prompt="storm trooper giving a speech", image=image, generator=generator).images[0]
depth_out.save('./images/depth_output.png')
评论