Image2Image diffusers pipeline with a prompt using stable cascade

[rohitgr7]

Is there any example of Image2Image diffusers pipeline with a prompt using stable cascade?

[tolgacangoz]

Hi @rohitgr7, @ekurtulus! It seems unclear 🤔:

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

pipeline = StableCascadeCombinedPipeline.from_pretrained(
    "stabilityai/stable-cascade", torch_dtype=torch.bfloat16, variant='bf16')
pipeline.enable_model_cpu_offload()
init_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png"
						).resize((512, 512))
prompt = "cat wizard, gandalf, lord of the rings, detailed, fantasy, cute, adorable, Pixar, Disney, 8k"
image = pipeline(prompt, images=[init_image], generator=torch.Generator('cpu').manual_seed(0)).images[0]
make_image_grid([init_image, image], rows=1, cols=2)