from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
import torch

repo_id = "stabilityai/stable-diffusion-2-base"
pipe = DiffusionPipeline.from_pretrained(repo_id, dtype=torch.float16, variant="fp16")

pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt = "High quality photo of an astronaut riding a horse in space"
image = pipe(prompt, num_inference_steps=25).images[0]
image

import torch
from diffusers import DiffusionPipeline, DPMSolverMultistepScheduler
from diffusers.utils import load_image, make_image_grid

img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"

init_image = load_image(img_url).resize((512, 512))
mask_image = load_image(mask_url).resize((512, 512))

repo_id = "stabilityai/stable-diffusion-2-inpainting"
pipe = DiffusionPipeline.from_pretrained(repo_id, dtype=torch.float16, variant="fp16")

pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
image = pipe(prompt=prompt, image=init_image, mask_image=mask_image, num_inference_steps=25).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

from diffusers import StableDiffusionUpscalePipeline
from diffusers.utils import load_image, make_image_grid
import torch

# load model and scheduler
model_id = "stabilityai/stable-diffusion-x4-upscaler"
pipeline = StableDiffusionUpscalePipeline.from_pretrained(model_id, dtype=torch.float16)
pipeline = pipeline.to("cuda")  # or "mps", "xpu", "cpu"

# let's download an  image
url = "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd2-upscale/low_res_cat.png"
low_res_img = load_image(url)
low_res_img = low_res_img.resize((128, 128))
prompt = "a white cat"
upscaled_image = pipeline(prompt=prompt, image=low_res_img).images[0]
make_image_grid([low_res_img.resize((512, 512)), upscaled_image.resize((512, 512))], rows=1, cols=2)

import torch
from diffusers import StableDiffusionDepth2ImgPipeline
from diffusers.utils import load_image, make_image_grid

pipe = StableDiffusionDepth2ImgPipeline.from_pretrained(
    "stabilityai/stable-diffusion-2-depth",
    dtype=torch.float16,
).to("cuda")  # or "mps", "xpu", "cpu"


url = "http://images.cocodataset.org/val2017/000000039769.jpg"
init_image = load_image(url)
prompt = "two tigers"
negative_prompt = "bad, deformed, ugly, bad anotomy"
image = pipe(prompt=prompt, image=init_image, negative_prompt=negative_prompt, strength=0.7).images[0]
make_image_grid([init_image, image], rows=1, cols=2)