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

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "kandinsky-community/kandinsky-2-2-decoder", dtype=torch.float16, 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()

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

prompt = "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
image = pipeline(prompt, image=init_image).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# pass prompt and image to pipeline
image = pipeline(prompt, image=init_image).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-refiner-1.0", 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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-sdxl-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# pass prompt and image to pipeline
image = pipeline(prompt, image=init_image, strength=0.5).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "kandinsky-community/kandinsky-2-2-decoder", dtype=torch.float16, 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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# pass prompt and image to pipeline
image = pipeline(prompt, image=init_image).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# pass prompt and image to pipeline
image = pipeline(prompt, image=init_image, strength=0.8).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# pass prompt and image to pipeline
image = pipeline(prompt, image=init_image, guidance_scale=8.0).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "stabilityai/stable-diffusion-xl-refiner-1.0", 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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
negative_prompt = "ugly, deformed, disfigured, poor details, bad anatomy"

# pass prompt and image to pipeline
image = pipeline(prompt, negative_prompt=negative_prompt, image=init_image).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
import torch
from diffusers.utils import 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("Astronaut in a jungle, cold color palette, muted colors, detailed, 8k").images[0]
text2image

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "kandinsky-community/kandinsky-2-2-decoder", dtype=torch.float16, 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()

image2image = pipeline("Astronaut in a jungle, cold color palette, muted colors, detailed, 8k", image=text2image).images[0]
make_image_grid([text2image, image2image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# pass prompt and image to pipeline
image = pipeline(prompt, image=init_image, output_type="latent").images[0]

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "ogkalu/Comic-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()

# need to include the token "charliebo artstyle" in the prompt to use this checkpoint
image = pipeline("Astronaut in a jungle, charliebo artstyle", image=image, output_type="latent").images[0]

pipeline = AutoPipelineForImage2Image.from_pretrained(
    "kohbanye/pixel-art-style", 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()

# need to include the token "pixelartstyle" in the prompt to use this checkpoint
image = pipeline("Astronaut in a jungle, pixelartstyle", image=image).images[0]
make_image_grid([init_image, image], rows=1, cols=2)

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

pipeline = AutoPipelineForImage2Image.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()

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"

# pass prompt and image to pipeline
image_1 = pipeline(prompt, image=init_image, output_type="latent").images[0]

from diffusers import StableDiffusionLatentUpscalePipeline

upscaler = StableDiffusionLatentUpscalePipeline.from_pretrained(
    "stabilityai/sd-x2-latent-upscaler", dtype=torch.float16, use_safetensors=True
)
upscaler.enable_model_cpu_offload()
upscaler.enable_xformers_memory_efficient_attention()

image_2 = upscaler(prompt, image=image_1).images[0]

from diffusers import StableDiffusionUpscalePipeline

super_res = StableDiffusionUpscalePipeline.from_pretrained(
    "stabilityai/stable-diffusion-x4-upscaler", dtype=torch.float16, variant="fp16", use_safetensors=True
)
super_res.enable_model_cpu_offload()
super_res.enable_xformers_memory_efficient_attention()

image_3 = super_res(prompt, image=image_2).images[0]
make_image_grid([init_image, image_3.resize((512, 512))], rows=1, cols=2)

from diffusers import AutoPipelineForImage2Image
import torch

pipeline = AutoPipelineForImage2Image.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()

image = pipeline(prompt_embeds=prompt_embeds, # generated from Compel
    negative_prompt_embeds=negative_prompt_embeds, # generated from Compel
    image=init_image,
).images[0]

from diffusers.utils import load_image, make_image_grid

# prepare image
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/img2img-init.png"
init_image = load_image(url)
init_image = init_image.resize((958, 960)) # resize to depth image dimensions
depth_image = load_image("https://huggingface.co/lllyasviel/control_v11f1p_sd15_depth/resolve/main/images/control.png")
make_image_grid([init_image, depth_image], rows=1, cols=2)

from diffusers import ControlNetModel, AutoPipelineForImage2Image
import torch

controlnet = ControlNetModel.from_pretrained("lllyasviel/control_v11f1p_sd15_depth", dtype=torch.float16, variant="fp16", use_safetensors=True)
pipeline = AutoPipelineForImage2Image.from_pretrained(
    "stable-diffusion-v1-5/stable-diffusion-v1-5", controlnet=controlnet, 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()

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image_control_net = pipeline(prompt, image=init_image, control_image=depth_image).images[0]
make_image_grid([init_image, depth_image, image_control_net], rows=1, cols=3)

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 astronaut in a jungle" # include the token "elden ring style" in the prompt
negative_prompt = "ugly, deformed, disfigured, poor details, bad anatomy"

image_elden_ring = pipeline(prompt, negative_prompt=negative_prompt, image=image_control_net, strength=0.45, guidance_scale=10.5).images[0]
make_image_grid([init_image, depth_image, image_control_net, image_elden_ring], rows=2, cols=2)

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

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