kandinsky-2-2-prior

Usage

Kandinsky 2.2 is available in diffusers!

pip install diffusers transformers accelerate

Text to image

from diffusers import AutoPipelineForText2Image
import torch

pipe = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "portrait of a young women, blue eyes, cinematic"
negative_prompt = "low quality, bad quality"

image = pipe(prompt=prompt, negative_prompt=negative_prompt, prior_guidance_scale =1.0, height=768, width=768).images[0]
image.save("portrait.png")

Text Guided Image-to-Image Generation

from PIL import Image
import requests
from io import BytesIO

url = "https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg"
response = requests.get(url)
original_image = Image.open(BytesIO(response.content)).convert("RGB")
original_image = original_image.resize((768, 512))

from diffusers import AutoPipelineForImage2Image
import torch

pipe = AutoPipelineForImage2Image.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()

prompt = "A fantasy landscape, Cinematic lighting"
negative_prompt = "low quality, bad quality"

image = pipe(prompt=prompt, image=original_image, strength=0.3, height=768, width=768).images[0]

out.images[0].save("fantasy_land.png")

Interpolate

from diffusers import KandinskyV22PriorPipeline, KandinskyV22Pipeline
from diffusers.utils import load_image
import PIL

import torch

pipe_prior = KandinskyV22PriorPipeline.from_pretrained(
    "kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16
)
pipe_prior.to("cuda")

img1 = load_image(
    "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main" "/kandinsky/cat.png"
)

img2 = load_image(
    "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main" "/kandinsky/starry_night.jpeg"
)

# add all the conditions we want to interpolate, can be either text or image
images_texts = ["a cat", img1, img2]

# specify the weights for each condition in images_texts
weights = [0.3, 0.3, 0.4]

# We can leave the prompt empty
prompt = ""
prior_out = pipe_prior.interpolate(images_texts, weights)

pipe = KandinskyV22Pipeline.from_pretrained("kandinsky-community/kandinsky-2-2-decoder", torch_dtype=torch.float16)
pipe.to("cuda")

image = pipe(**prior_out, height=768, width=768).images[0]

image.save("starry_cat.png")

Text Guided Inpainting Generation

from diffusers import AutoPipelineForInpainting
from diffusers.utils import load_image
import torch
import numpy as np

pipe = AutoPipelineForInpainting.from_pretrained("kandinsky-community/kandinsky-2-2-decoder-inpaint", torch_dtype=torch.float16)
pipe.enable_model_cpu_offload()

prompt = "a hat"

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

mask = np.zeros((768, 768), dtype=np.float32)
# Let's mask out an area above the cat's head
mask[:250, 250:-250] = 1

out = pipe(
    prompt=prompt,
    image=init_image,
    mask_image=mask,
    height=768,
    width=768,
    num_inference_steps=150,
)

image = out.images[0]
image.save("cat_with_hat.png")

Breaking change on the mask input:

We introduced a breaking change for Kandinsky inpainting pipeline in the following pull request: https://github.com/huggingface/diffusers/pull/4207. Previously we accepted a mask format where black pixels represent the masked-out area. We have changed to use white pixels to represent masks instead in order to have a unified mask format across all our pipelines. Please upgrade your inpainting code to follow the above. If you are using Kandinsky Inpaint in production. You now need to change the mask to:

# For PIL input
import PIL.ImageOps
mask = PIL.ImageOps.invert(mask)

# For PyTorch and Numpy input
mask = 1 - mask

Text-to-Image Generation with ControlNet Conditioning

import torch
import numpy as np

from transformers import pipeline
from diffusers.utils import load_image

from diffusers import KandinskyV22PriorPipeline, KandinskyV22ControlnetPipeline

# let's take an image and extract its depth map.
def make_hint(image, depth_estimator):
    image = depth_estimator(image)["depth"]
    image = np.array(image)
    image = image[:, :, None]
    image = np.concatenate([image, image, image], axis=2)
    detected_map = torch.from_numpy(image).float() / 255.0
    hint = detected_map.permute(2, 0, 1)
    return hint

img = load_image(
    "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/cat.png"
).resize((768, 768))

# We can use the `depth-estimation` pipeline from transformers to process the image and retrieve its depth map.
depth_estimator = pipeline("depth-estimation")
hint = make_hint(img, depth_estimator).unsqueeze(0).half().to("cuda")

# Now, we load the prior pipeline and the text-to-image controlnet pipeline
pipe_prior = KandinskyV22PriorPipeline.from_pretrained(
    "kandinsky-community/kandinsky-2-2-prior", torch_dtype=torch.float16
)
pipe_pri