T2i Adapter Depth Zoe Sdxl 1.0

🚀 T2I-Adapter-SDXL - Depth-Zoe

T2I Adapter is a network that provides additional conditioning for 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 offers depth conditioning for the StableDiffusionXL checkpoint. It is a collaborative effort between Tencent ARC and Hugging Face.

🚀 Quick Start

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 timm==0.6.12 # for conditioning models and detectors
pip install transformers accelerate safetensors

1. Download images in the appropriate control image format.
2. Pass the control image and prompt to the StableDiffusionXLAdapterPipeline.

✨ Features

• Additional Conditioning: T2I Adapter provides extra conditioning to Stable Diffusion, enabling more controllable image generation.
• Depth Conditioning: This checkpoint offers depth conditioning for the StableDiffusionXL checkpoint.
• Multiple Checkpoints: There are multiple checkpoints available, each taking a different type of conditioning as input.

📦 Installation

The installation steps are included in the Quick Start section.

💻 Usage Examples

Basic Usage

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

# load adapter
adapter = T2IAdapter.from_pretrained(
  "TencentARC/t2i-adapter-depth-zoe-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()

zoe_depth = ZoeDetector.from_pretrained(
    "valhalla/t2iadapter-aux-models", filename="zoed_nk.pth", model_type="zoedepth_nk"
).to("cuda")

Advanced Usage

# Condition Image
url = "https://huggingface.co/Adapter/t2iadapter/resolve/main/figs_SDXLV1.0/org_zeo.jpg"
image = load_image(url)
image = zoe_depth(image, gamma_corrected=True, detect_resolution=512, image_resolution=1024)

# Generation
prompt = "A photo of a orchid, 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_zoe.png')

📚 Documentation

Model Details

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.
TencentARC/t2i-adapter-openpose-sdxl-1.0 Trained with OpenPose bone image	A OpenPose bone image.

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: 25000
• 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

📄 License

This model is licensed under the Apache 2.0 license.