text-to-image-image-to-text

from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
import torch
from diffusers.utils import make_image_grid

pipeline = AutoPipelineForText2Image.from_pretrained(
    "runwayml/stable-diffusion-v1-5", torch_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", torch_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(
    "runwayml/stable-diffusion-v1-5", torch_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", torch_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", torch_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(
    "runwayml/stable-diffusion-v1-5", torch_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", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
)
upscaler.enable_model_cpu_offload()
upscaler.enable_xformers_memory_efficient_attention()

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

from diffusers import StableDiffusionUpscalePipeline

super_res = StableDiffusionUpscalePipeline.from_pretrained(
    "stabilityai/stable-diffusion-x4-upscaler", torch_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)