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

pipeline = AutoPipelineForInpainting.from_pretrained(
    "kandinsky-community/kandinsky-2-2-decoder-inpaint", dtype=torch.float16
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

prompt = "a black cat with glowing eyes, cute, adorable, disney, pixar, highly detailed, 8k"
negative_prompt = "bad anatomy, deformed, ugly, disfigured"
image = pipeline(prompt=prompt, negative_prompt=negative_prompt, image=init_image, mask_image=mask_image).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

import torch
from diffusers import AutoPipelineForInpainting
from diffusers.utils import load_image
from PIL import Image

pipeline = AutoPipelineForInpainting.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", dtype=torch.float16).to('cuda')  # or "mps", "xpu", "cpu"

mask = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/seashore_mask.png")
blurred_mask = pipeline.mask_processor.blur(mask, blur_factor=33)
blurred_mask

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

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting", dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

generator = torch.Generator("cuda").manual_seed(92)
prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image, generator=generator).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

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

pipeline = AutoPipelineForInpainting.from_pretrained(
    "diffusers/stable-diffusion-xl-1.0-inpainting-0.1", dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

generator = torch.Generator("cuda").manual_seed(92)
prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image, generator=generator).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

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

pipeline = AutoPipelineForInpainting.from_pretrained(
    "kandinsky-community/kandinsky-2-2-decoder-inpaint", dtype=torch.float16
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

generator = torch.Generator("cuda").manual_seed(92)
prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image, generator=generator).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

import PIL
import numpy as np
import torch

from diffusers import AutoPipelineForInpainting
from diffusers.utils import load_image, make_image_grid

device = "cuda"  # or "mps", "xpu", "cpu"
pipeline = AutoPipelineForInpainting.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting",
    dtype=torch.float16,
    variant="fp16"
)
pipeline = pipeline.to(device)

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))

prompt = "Face of a yellow cat, high resolution, sitting on a park bench"
repainted_image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image).images[0]
repainted_image.save("repainted_image.png")

unmasked_unchanged_image = pipeline.image_processor.apply_overlay(mask_image, init_image, repainted_image)
unmasked_unchanged_image.save("force_unmasked_unchanged.png")
make_image_grid([init_image, mask_image, repainted_image, unmasked_unchanged_image], rows=2, cols=2)

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

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting", dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image, strength=0.6).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

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

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting", dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image, guidance_scale=2.5).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

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

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting", dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
negative_prompt = "bad architecture, unstable, poor details, blurry"
image = pipeline(prompt=prompt, negative_prompt=negative_prompt, image=init_image, mask_image=mask_image).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

import torch
from diffusers import AutoPipelineForInpainting
from diffusers.utils import load_image
from PIL import Image

generator = torch.Generator(device='cuda').manual_seed(0)  # or "mps", "xpu", "cpu"
pipeline = AutoPipelineForInpainting.from_pretrained("stable-diffusion-v1-5/stable-diffusion-v1-5", dtype=torch.float16).to('cuda')

base = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/seashore.png")
mask = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/seashore_mask.png")

image = pipeline("boat", image=base, mask_image=mask, strength=0.75, generator=generator, padding_mask_crop=32).images[0]
image

import torch
from diffusers import AutoPipelineForText2Image, AutoPipelineForInpainting
from diffusers.utils import load_image, make_image_grid

pipeline = AutoPipelineForText2Image.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5", dtype=torch.float16, variant="fp16", use_safetensors=True
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

text2image = pipeline("concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k").images[0]

mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_text-chain-mask.png")

pipeline = AutoPipelineForInpainting.from_pretrained(
    "kandinsky-community/kandinsky-2-2-decoder-inpaint", dtype=torch.float16
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

prompt = "digital painting of a fantasy waterfall, cloudy"
image = pipeline(prompt=prompt, image=text2image, mask_image=mask_image).images[0]
make_image_grid([text2image, mask_image, image], rows=1, cols=3)

import torch
from diffusers import AutoPipelineForInpainting, AutoPipelineForImage2Image
from diffusers.utils import load_image, make_image_grid

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting", dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
image_inpainting = pipeline(prompt=prompt, image=init_image, mask_image=mask_image).images[0]

# resize image to 1024x1024 for SDXL
image_inpainting = image_inpainting.resize((1024, 1024))

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stabilityai/stable-diffusion-xl-refiner-1.0", dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

image = pipeline(prompt=prompt, image=image_inpainting, mask_image=mask_image, output_type="latent").images[0]

pipeline = AutoPipelineForImage2Image.from_pipe(pipeline)
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

image = pipeline(prompt=prompt, image=image).images[0]
make_image_grid([init_image, mask_image, image_inpainting, image], rows=2, cols=2)

import torch
from diffusers import AutoPipelineForInpainting
from diffusers.utils import make_image_grid

pipeline = AutoPipelineForInpainting.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting", dtype=torch.float16,
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

image = pipeline(prompt_embeds=prompt_embeds, # generated from Compel
    negative_prompt_embeds=negative_prompt_embeds, # generated from Compel
    image=init_image,
    mask_image=mask_image
).images[0]
make_image_grid([init_image, mask_image, image], rows=1, cols=3)

import torch
import numpy as np
from diffusers import ControlNetModel, StableDiffusionControlNetInpaintPipeline
from diffusers.utils import load_image, make_image_grid

# load ControlNet
controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11p_sd15_inpaint", dtype=torch.float16, variant="fp16")

# pass ControlNet to the pipeline
pipeline = StableDiffusionControlNetInpaintPipeline.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-inpainting", controlnet=controlnet, dtype=torch.float16, variant="fp16"
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

# load base and mask image
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png")
mask_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint_mask.png")

# prepare control image
def make_inpaint_condition(init_image, mask_image):
    init_image = np.array(init_image.convert("RGB")).astype(np.float32) / 255.0
    mask_image = np.array(mask_image.convert("L")).astype(np.float32) / 255.0

    assert init_image.shape[0:1] == mask_image.shape[0:1], "image and image_mask must have the same image size"
    init_image[mask_image > 0.5] = -1.0  # set as masked pixel
    init_image = np.expand_dims(init_image, 0).transpose(0, 3, 1, 2)
    init_image = torch.from_numpy(init_image)
    return init_image

control_image = make_inpaint_condition(init_image, mask_image)

prompt = "concept art digital painting of an elven castle, inspired by lord of the rings, highly detailed, 8k"
image = pipeline(prompt=prompt, image=init_image, mask_image=mask_image, control_image=control_image).images[0]
make_image_grid([init_image, mask_image, PIL.Image.fromarray(np.uint8(control_image[0][0])).convert('RGB'), image], rows=2, cols=2)

from diffusers import AutoPipelineForImage2Image

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "nitrosocke/elden-ring-diffusion", dtype=torch.float16,
)
pipeline.enable_model_cpu_offload()
# remove following line if xFormers is not installed or you have PyTorch 2.0 or higher installed
pipeline.enable_xformers_memory_efficient_attention()

prompt = "elden ring style castle" # include the token "elden ring style" in the prompt
negative_prompt = "bad architecture, deformed, disfigured, poor details"

image_elden_ring = pipeline(prompt, negative_prompt=negative_prompt, image=image).images[0]
make_image_grid([init_image, mask_image, image, image_elden_ring], rows=2, cols=2)

+ pipeline.enable_xformers_memory_efficient_attention()
+ pipeline.enable_model_cpu_offload()

pipeline.unet = torch.compile(pipeline.unet, mode="reduce-overhead", fullgraph=True)