README.md

---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- controlnet
inference: true
---
    
# SDXL-controlnet: Canny

These are controlnet weights trained on stabilityai/stable-diffusion-xl-base-1.0 with canny conditioning. You can find some example images in the following. 

prompt: a couple watching a romantic sunset, 4k photo
![images_0)](./out_couple.png)

prompt: ultrarealistic shot of a furry blue bird
![images_1)](./out_bird.png)

prompt: a woman, close up, detailed, beautiful, street photography, photorealistic, detailed, Kodak ektar 100, natural, candid shot
![images_2)](./out_women.png)

prompt: Cinematic, neoclassical table in the living room, cinematic, contour, lighting, highly detailed, winter, golden hour
![images_3)](./out_room.png)

prompt: a tornado hitting grass field, 1980's film grain. overcast, muted colors.
![images_0)](./out_tornado.png)

## Usage

```python
from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
from diffusers.utils import load_image
from PIL import Image
import torch
import numpy as np
import cv2

prompt = "aerial view, a futuristic research complex in a bright foggy jungle, hard lighting"
negative_prompt = 'low quality, bad quality, sketches'

image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd_controlnet/hf-logo.png")

controlnet_conditioning_scale = 0.5  # recommended for good generalization

controlnet = ControlNetModel.from_pretrained(
    "diffusers/controlnet-sdxl-1.0", subfolder="checkpoint-3000/controlnet", torch_dtype=torch.float16
)
vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
    "stabilityai/stable-diffusion-xl-base-1.0",
    controlnet=controlnet,
    torch_dtype=torch.float16,
)
pipe.enable_model_cpu_offload()

image = np.array(image)
image = cv2.Canny(image, 100, 200)
image = image[:, :, None]
image = np.concatenate([image, image, image], axis=2)
image = Image.fromarray(image)

images = pipe(
    prompt, image=image, controlnet_conditioning_scale=controlnet_conditioning_scale,
    ).images

image[0]_.save(f"hug_lab.png")
```