T2I Adapter - Canny

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 edge's 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

Example

1. Dependencies

pip install diffusers transformers opencv-contrib-python

2. Run code:

import cv2
from PIL import Image
import torch
import numpy as np
from diffusers import T2IAdapter, StableDiffusionAdapterPipeline

image = Image.open('./images/canny_input.png')
image = np.array(image)

low_threshold = 100
high_threshold = 200

image = cv2.Canny(image, low_threshold, high_threshold)
image = Image.fromarray(image)

image.save('./images/canny.png')

adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_canny_sd15v2", torch_dtype=torch.float16)
pipe = StableDiffusionAdapterPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    adapter=adapter,
    torch_dtype=torch.float16,
)
pipe.to("cuda")

generator = torch.manual_seed(0)

out_image = pipe(
    "a rabbit wearing glasses",
    image=image,
    generator=generator,
).images[0]

out_image.save('./images/canny_out.png')