metadata

license: apache-2.0
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
  - art
  - t2i-adapter
  - image-to-image
  - stable-diffusion-xl-diffusers
  - stable-diffusion-xl

T2I-Adapter-SDXL - Openpose

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 openpose for the StableDiffusionXL checkpoint. This was a collaboration between Tencent ARC and Hugging Face.

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.
Model complexity:

SD-V1.4/1.5 SD-XL T2I-Adapter T2I-Adapter-SDXL

Parameters 860M 2.6B 77 M 77/79 M
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} }

	SD-V1.4/1.5	SD-XL	T2I-Adapter	T2I-Adapter-SDXL
Parameters	860M	2.6B	77 M	77/79 M

Checkpoints

Model Name	Control Image Overview	Control Image Example	Generated Image Example
TencentARC/t2i-adapter-canny-sdxl-1.0 Trained with canny edge detection	A monochrome image with white edges on a black background.
TencentARC/t2i-adapter-sketch-sdxl-1.0 Trained with PidiNet edge detection	A hand-drawn monochrome image with white outlines on a black background.
TencentARC/t2i-adapter-lineart-sdxl-1.0 Trained with lineart edge detection	A hand-drawn monochrome image with white outlines on a black background.
TencentARC/t2i-adapter-depth-midas-sdxl-1.0 Trained with Midas depth estimation	A grayscale image with black representing deep areas and white representing shallow areas.
TencentARC/t2i-adapter-depth-zoe-sdxl-1.0 Trained with Zoe depth estimation	A grayscale image with black representing deep areas and white representing shallow areas.
Adapter/t2iadapter_openpose_sdxlv1 Trained with OpenPose bone image	A OpenPose bone image.

Example

To get started, first install the required dependencies:

pip install git+https://github.com/huggingface/diffusers.git@t2iadapterxl # for now
pip install -U controlnet_aux==0.0.7 # for conditioning models and detectors
pip install transformers accelerate safetensors

Images are first downloaded into the appropriate control image format.
The control image and prompt are passed to the StableDiffusionXLAdapterPipeline.

Let's have a look at a simple example using the Openpose Adapter.

Dependency

from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, EulerAncestralDiscreteScheduler, AutoencoderKL
from diffusers.utils import load_image, make_image_grid
from controlnet_aux import OpenposeDetector
import torch
import numpy as np
from PIL import Image

# load adapter
adapter = T2IAdapter.from_pretrained(
  "TencentARC/t2i-adapter-openpose-sdxl-1.0", torch_dtype=torch.float16
).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)
pipe = StableDiffusionXLAdapterPipeline.from_pretrained(
    model_id, vae=vae, adapter=adapter, scheduler=euler_a, torch_dtype=torch.float16, variant="fp16", 
).to("cuda")
pipe.enable_xformers_memory_efficient_attention()

open_pose = OpenposeDetector.from_pretrained("lllyasviel/Annotators")

Condition Image

url = "https://huggingface.co/Adapter/t2iadapter/resolve/main/people.jpg"
image = load_image(url)
image = open_pose(image, detect_resolution=512, image_resolution=1024)
image = np.array(image)[:, :, ::-1]           
image = Image.fromarray(np.uint8(image))

Generation

prompt = "A couple, 4k photo, highly detailed"
negative_prompt = "anime, cartoon, graphic, text, painting, crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured"

gen_images = pipe(
  prompt=prompt,
  negative_prompt=negative_prompt,
  image=image,
  num_inference_steps=30,
  adapter_conditioning_scale=1,
  guidance_scale=7.5,  
).images[0]
gen_images.save('out_pose.png')

Training

Our training script was built on top of the official training script that we provide here.

The model is trained on 3M high-resolution image-text pairs from LAION-Aesthetics V2 with

Training steps: 35000
Batch size: Data parallel with a single gpu batch size of 16 for a total batch size of 256.
Learning rate: Constant learning rate of 1e-5.
Mixed precision: fp16