metadata
license: apache-2.0
china-chic-style on stable diffuison by dreambooth
Here are the images used for training this concept:
new concept
china-chic-style
inference
from torch import autocast
from diffusers import StableDiffusionPipeline
import torch
import diffusers
from PIL import Image
def image_grid(imgs, rows, cols):
assert len(imgs) == rows*cols
w, h = imgs[0].size
grid = Image.new('RGB', size=(cols*w, rows*h))
grid_w, grid_h = grid.size
for i, img in enumerate(imgs):
grid.paste(img, box=(i%cols*w, i//cols*h))
return grid
pipe = StableDiffusionPipeline.from_pretrained("Dushwe/china-chic-landscape").to("cuda")
prompt = 'the moon hanging high in the sky,chinc-chic-style'
images = pipe(prompt, num_images_per_prompt=1, num_inference_steps=50, guidance_scale=7.5,torch_dtype=torch.cuda.HalfTensor).images
grid = image_grid(images, 1, 1)
grid
You run your new concept via diffusers
Colab Notebook for Inference. Don't forget to use the concept prompts!