T2I-Adapter-SDXL - Depth-MiDaS

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 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} }

Checkpoints

Example

To get started, first install the required dependencies:

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

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

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

• Dependency

from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, EulerAncestralDiscreteScheduler, AutoencoderKL
from diffusers.utils import load_image, make_image_grid
from controlnet_aux.midas import MidasDetector
import torch

# load adapter
adapter = T2IAdapter.from_pretrained(
  "TencentARC/t2i-adapter-depth-midas-sdxl-1.0", torch_dtype=torch.float16, varient="fp16"
).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()

midas_depth = MidasDetector.from_pretrained(
  "valhalla/t2iadapter-aux-models", filename="dpt_large_384.pt", model_type="dpt_large"
).to("cuda")

• Condition Image

url = "https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_mid.jpg"
image = load_image(url)
image = midas_depth(
  image, detect_resolution=512, image_resolution=1024
)

• Generation

prompt = "A photo of a room, 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_mid.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