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

# T2I-Adapter-SDXL - Lineart

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 for the StableDiffusionXL 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](https://github.com/TencentARC/T2I-Adapter), [Paper](https://arxiv.org/abs/2302.08453).
- **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 |
|---|---|---|---|
|[Adapter/t2iadapter_canny_sdxlv1](https://huggingface.co/Adapter/t2iadapter_canny_sdxlv1)<br/> *Trained with canny edge detection* | A monochrome image with white edges on a black background.|<a href=""><img width="64" style="margin:0;padding:0;" src=""/></a>|<a href=""><img width="64" src=""/></a>|
|[Adapter/t2iadapter_sketch_sdxlv1](https://huggingface.co/Adapter/t2iadapter_sketch_sdxlv1)<br/> *Trained with [PidiNet](https://github.com/zhuoinoulu/pidinet) edge detection* | A hand-drawn monochrome image with white outlines on a black background.|<a href=""><img width="64" style="margin:0;padding:0;" src=""/></a>|<a href=""><img width="64" src=""/></a>|
|[Adapter/t2iadapter_depth_sdxlv1](https://huggingface.co/Adapter/t2iadapter_depth_sdxlv1)<br/> *Trained with Midas depth estimation*  | A grayscale image with black representing deep areas and white representing shallow areas.|<a href=""><img width="64" src=""/></a>|<a href=""><img width="64" src=""/></a>|
|[Adapter/t2iadapter_openpose_sdxlv1](https://huggingface.co/Adapter/t2iadapter_openpose_sdxlv1)<br/> *Trained with OpenPose bone image*  | A [OpenPose bone](https://github.com/CMU-Perceptual-Computing-Lab/openpose) image.|<a href=""><img width="64" src=""/></a>|<a href=""><img width="64" src=""/></a>|


## Example

To get started, first install the required dependencies:

```bash
pip install git+https://github.com/huggingface/diffusers.git@t2iadapterxl # for now
pip install git+https://github.com/patrickvonplaten/controlnet_aux.git # 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`](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/t2i_adapter/pipeline_stable_diffusion_xl_adapter.py#L125).

Let's have a look at a simple example using the [Canny Adapter](https://huggingface.co/Adapter/t2iadapter_canny_sdxlv1).

```py
from diffusers import StableDiffusionXLAdapterPipeline, T2IAdapter, EulerAncestralDiscreteScheduler
from diffusers.utils import load_image, make_image_grid
from controlnet_aux.lineart import LineartDetector

# load adapter
adapter = T2IAdapter.from_pretrained(
  "Adapter/t2i-adapter-lineart-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()

# Load PidiNet
line_detector = LineartDetector.from_pretrained("lllyasviel/Annotators").to("cuda")

url = "https://cdn.sortiraparis.com/images/80/77381/729517-oppenheimer-le-prochain-film-de-christopher-nolan-pour-2023-la-premiere-photo.jpg"
image = load_image(url)
image = line_detector(
  image.resize((384, 384)), detect_resolution=384, image_resolution=1024
).resize((1024, 1024))

prompt = "cinematic still, a man, head shot"
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, 
    cond_tau=1
).images
gen_images[0]
```