T2I Adapter - Color

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 color palettes for the stable diffusion 1.4 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

1. Dependencies

pip install diffusers transformers

2. Run code:

from PIL import Image
import torch
from diffusers import StableDiffusionAdapterPipeline, T2IAdapter

image = Image.open('./images/color_ref.png')

color_palette = image.resize((8, 8))
color_palette = color_palette.resize((512, 512), resample=Image.Resampling.NEAREST)

color_palette.save('./images/color_palette.png')

adapter = T2IAdapter.from_pretrained("TencentARC/t2iadapter_color_sd14v1", torch_dtype=torch.float16)
pipe = StableDiffusionAdapterPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    adapter=adapter,
    torch_dtype=torch.float16,
)
pipe.to("cuda")

generator = torch.manual_seed(0)

out_image = pipe(
    "At night, glowing cubes in front of the beach",
    image=color_palette,
    generator=generator,
).images[0]

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