pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", custom_pipeline="filename_in_the_community_folder")

import torch
from torchvision import transforms

from diffusers import DPMSolverMultistepScheduler
from diffusers.utils import load_image
from examples.community.pipeline_stable_diffusion_xl_differential_img2img import (
    StableDiffusionXLDifferentialImg2ImgPipeline,
)


pipeline = StableDiffusionXLDifferentialImg2ImgPipeline.from_pretrained(
    "SG161222/RealVisXL_V4.0", torch_dtype=torch.float16, variant="fp16"
).to("cuda")
pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config, use_karras_sigmas=True)


def preprocess_image(image):
    image = image.convert("RGB")
    image = transforms.CenterCrop((image.size[1] // 64 * 64, image.size[0] // 64 * 64))(image)
    image = transforms.ToTensor()(image)
    image = image * 2 - 1
    image = image.unsqueeze(0).to("cuda")
    return image


def preprocess_map(map):
    map = map.convert("L")
    map = transforms.CenterCrop((map.size[1] // 64 * 64, map.size[0] // 64 * 64))(map)
    map = transforms.ToTensor()(map)
    map = map.to("cuda")
    return map


image = preprocess_image(
    load_image(
        "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/20240329211129_4024911930.png?download=true"
    )
)

mask = preprocess_map(
    load_image(
        "https://huggingface.co/datasets/OzzyGT/testing-resources/resolve/main/differential/gradient_mask.png?download=true"
    )
)

prompt = "a green pear"
negative_prompt = "blurry"

image = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    guidance_scale=7.5,
    num_inference_steps=25,
    original_image=image,
    image=image,
    strength=1.0,
    map=mask,
).images[0]

image.save("result.png")

import torch
from diffusers import DiffusionPipeline, DDIMScheduler
from diffusers.utils import load_image, make_image_grid

pipe = DiffusionPipeline.from_pretrained(
    "stabilityai/stable-diffusion-2-inpainting",
    custom_pipeline="hd_painter"
)
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)

prompt = "wooden boat"
init_image = load_image("https://raw.githubusercontent.com/Picsart-AI-Research/HD-Painter/main/__assets__/samples/images/2.jpg")
mask_image = load_image("https://raw.githubusercontent.com/Picsart-AI-Research/HD-Painter/main/__assets__/samples/masks/2.png")

image = pipe (prompt, init_image, mask_image, use_rasg = True, use_painta = True, generator=torch.manual_seed(12345)).images[0]

make_image_grid([init_image, mask_image, image], rows=1, cols=3)

import numpy as np
import torch
from PIL import Image
from diffusers import DiffusionPipeline
from diffusers.utils import load_image

# Original DDIM version (higher quality)
pipe = DiffusionPipeline.from_pretrained(
    "prs-eth/marigold-v1-0",
    custom_pipeline="marigold_depth_estimation"
    # torch_dtype=torch.float16,                # (optional) Run with half-precision (16-bit float).
    # variant="fp16",                           # (optional) Use with `torch_dtype=torch.float16`, to directly load fp16 checkpoint
)

# (New) LCM version (faster speed)
pipe = DiffusionPipeline.from_pretrained(
    "prs-eth/marigold-lcm-v1-0",
    custom_pipeline="marigold_depth_estimation"
    # torch_dtype=torch.float16,                # (optional) Run with half-precision (16-bit float).
    # variant="fp16",                           # (optional) Use with `torch_dtype=torch.float16`, to directly load fp16 checkpoint
)

pipe.to("cuda")

img_path_or_url = "https://share.phys.ethz.ch/~pf/bingkedata/marigold/pipeline_example.jpg"
image: Image.Image = load_image(img_path_or_url)

pipeline_output = pipe(
    image,                    # Input image.
    # ----- recommended setting for DDIM version -----
    # denoising_steps=10,     # (optional) Number of denoising steps of each inference pass. Default: 10.
    # ensemble_size=10,       # (optional) Number of inference passes in the ensemble. Default: 10.
    # ------------------------------------------------

    # ----- recommended setting for LCM version ------
    # denoising_steps=4,
    # ensemble_size=5,
    # -------------------------------------------------

    # processing_res=768,     # (optional) Maximum resolution of processing. If set to 0: will not resize at all. Defaults to 768.
    # match_input_res=True,   # (optional) Resize depth prediction to match input resolution.
    # batch_size=0,           # (optional) Inference batch size, no bigger than `num_ensemble`. If set to 0, the script will automatically decide the proper batch size. Defaults to 0.
    # seed=2024,              # (optional) Random seed can be set to ensure additional reproducibility. Default: None (unseeded). Note: forcing --batch_size 1 helps to increase reproducibility. To ensure full reproducibility, deterministic mode needs to be used.
    # color_map="Spectral",   # (optional) Colormap used to colorize the depth map. Defaults to "Spectral". Set to `None` to skip colormap generation.
    # show_progress_bar=True, # (optional) If true, will show progress bars of the inference progress.
)

depth: np.ndarray = pipeline_output.depth_np                    # Predicted depth map
depth_colored: Image.Image = pipeline_output.depth_colored      # Colorized prediction

# Save as uint16 PNG
depth_uint16 = (depth * 65535.0).astype(np.uint16)
Image.fromarray(depth_uint16).save("./depth_map.png", mode="I;16")

# Save colorized depth map
depth_colored.save("./depth_colored.png")

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "longlian/lmd_plus",
    custom_pipeline="llm_grounded_diffusion",
    custom_revision="main",
    variant="fp16", torch_dtype=torch.float16
)
pipe.enable_model_cpu_offload()

# Generate directly from a text prompt and an LLM response
prompt = "a waterfall and a modern high speed train in a beautiful forest with fall foliage"
phrases, boxes, bg_prompt, neg_prompt = pipe.parse_llm_response("""
[('a waterfall', [71, 105, 148, 258]), ('a modern high speed train', [255, 223, 181, 149])]
Background prompt: A beautiful forest with fall foliage
Negative prompt:
""")

images = pipe(
    prompt=prompt,
    negative_prompt=neg_prompt,
    phrases=phrases,
    boxes=boxes,
    gligen_scheduled_sampling_beta=0.4,
    output_type="pil",
    num_inference_steps=50,
    lmd_guidance_kwargs={}
).images

images[0].save("./lmd_plus_generation.jpg")

import torch
from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained(
    "longlian/lmd_plus",
    custom_pipeline="llm_grounded_diffusion",
    variant="fp16", torch_dtype=torch.float16
)
pipe.enable_model_cpu_offload()

# Generate an image described by the prompt and
# insert objects described by text at the region defined by bounding boxes
prompt = "a waterfall and a modern high speed train in a beautiful forest with fall foliage"
boxes = [[0.1387, 0.2051, 0.4277, 0.7090], [0.4980, 0.4355, 0.8516, 0.7266]]
phrases = ["a waterfall", "a modern high speed train"]

images = pipe(
    prompt=prompt,
    phrases=phrases,
    boxes=boxes,
    gligen_scheduled_sampling_beta=0.4,
    output_type="pil",
    num_inference_steps=50,
    lmd_guidance_kwargs={}
).images

images[0].save("./lmd_plus_generation.jpg")

from diffusers import DiffusionPipeline
from transformers import CLIPImageProcessor, CLIPModel
import torch


feature_extractor = CLIPImageProcessor.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K")
clip_model = CLIPModel.from_pretrained("laion/CLIP-ViT-B-32-laion2B-s34B-b79K", torch_dtype=torch.float16)


guided_pipeline = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    custom_pipeline="clip_guided_stable_diffusion",
    clip_model=clip_model,
    feature_extractor=feature_extractor,

    torch_dtype=torch.float16,
)
guided_pipeline.enable_attention_slicing()
guided_pipeline = guided_pipeline.to("cuda")

prompt = "fantasy book cover, full moon, fantasy forest landscape, golden vector elements, fantasy magic, dark light night, intricate, elegant, sharp focus, illustration, highly detailed, digital painting, concept art, matte, art by WLOP and Artgerm and Albert Bierstadt, masterpiece"

generator = torch.Generator(device="cuda").manual_seed(0)
images = []
for i in range(4):
    image = guided_pipeline(
        prompt,
        num_inference_steps=50,
        guidance_scale=7.5,
        clip_guidance_scale=100,
        num_cutouts=4,
        use_cutouts=False,
        generator=generator,
    ).images[0]
    images.append(image)

# save images locally
for i, img in enumerate(images):
    img.save(f"./clip_guided_sd/image_{i}.png")

from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained("google/ddpm-cifar10-32", custom_pipeline="one_step_unet")
pipe()

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    revision='fp16',
    torch_dtype=torch.float16,
    safety_checker=None,  # Very important for videos...lots of false positives while interpolating
    custom_pipeline="interpolate_stable_diffusion",
).to('cuda')
pipe.enable_attention_slicing()

frame_filepaths = pipe.walk(
    prompts=['a dog', 'a cat', 'a horse'],
    seeds=[42, 1337, 1234],
    num_interpolation_steps=16,
    output_dir='./dreams',
    batch_size=4,
    height=512,
    width=512,
    guidance_scale=8.5,
    num_inference_steps=50,
)

#!/usr/bin/env python3
from diffusers import DiffusionPipeline
import PIL
import requests
from io import BytesIO
import torch


def download_image(url):
    response = requests.get(url)
    return PIL.Image.open(BytesIO(response.content)).convert("RGB")

pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", custom_pipeline="stable_diffusion_mega", torch_dtype=torch.float16, revision="fp16")
pipe.to("cuda")
pipe.enable_attention_slicing()


### Text-to-Image

images = pipe.text2img("An astronaut riding a horse").images

### Image-to-Image

init_image = download_image("https://raw.githubusercontent.com/CompVis/stable-diffusion/main/assets/stable-samples/img2img/sketch-mountains-input.jpg")

prompt = "A fantasy landscape, trending on artstation"

images = pipe.img2img(prompt=prompt, image=init_image, strength=0.75, guidance_scale=7.5).images

### Inpainting

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 = download_image(img_url).resize((512, 512))
mask_image = download_image(mask_url).resize((512, 512))

prompt = "a cat sitting on a bench"
images = pipe.inpaint(prompt=prompt, image=init_image, mask_image=mask_image, strength=0.75).images

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    'hakurei/waifu-diffusion',
    custom_pipeline="lpw_stable_diffusion",

    torch_dtype=torch.float16
)
pipe=pipe.to("cuda")

prompt = "best_quality (1girl:1.3) bow bride brown_hair closed_mouth frilled_bow frilled_hair_tubes frills (full_body:1.3) fox_ear hair_bow hair_tubes happy hood japanese_clothes kimono long_sleeves red_bow smile solo tabi uchikake white_kimono wide_sleeves cherry_blossoms"
neg_prompt = "lowres, bad_anatomy, error_body, error_hair, error_arm, error_hands, bad_hands, error_fingers, bad_fingers, missing_fingers, error_legs, bad_legs, multiple_legs, missing_legs, error_lighting, error_shadow, error_reflection, text, error, extra_digit, fewer_digits, cropped, worst_quality, low_quality, normal_quality, jpeg_artifacts, signature, watermark, username, blurry"

pipe.text2img(prompt, negative_prompt=neg_prompt, width=512,height=512,max_embeddings_multiples=3).images[0]

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    'CompVis/stable-diffusion-v1-4',
    custom_pipeline="lpw_stable_diffusion_onnx",
    revision="onnx",
    provider="CUDAExecutionProvider"
)

prompt = "a photo of an astronaut riding a horse on mars, best quality"
neg_prompt = "lowres, bad anatomy, error body, error hair, error arm, error hands, bad hands, error fingers, bad fingers, missing fingers, error legs, bad legs, multiple legs, missing legs, error lighting, error shadow, error reflection, text, error, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry"

pipe.text2img(prompt,negative_prompt=neg_prompt, width=512, height=512, max_embeddings_multiples=3).images[0]

import torch

import matplotlib.pyplot as plt
from datasets import load_dataset
from diffusers import DiffusionPipeline
from transformers import (
    WhisperForConditionalGeneration,
    WhisperProcessor,
)


device = "cuda" if torch.cuda.is_available() else "cpu"

ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")

audio_sample = ds[3]

text = audio_sample["text"].lower()
speech_data = audio_sample["audio"]["array"]

model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small").to(device)
processor = WhisperProcessor.from_pretrained("openai/whisper-small")

diffuser_pipeline = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="speech_to_image_diffusion",
    speech_model=model,
    speech_processor=processor,

    torch_dtype=torch.float16,
)

diffuser_pipeline.enable_attention_slicing()
diffuser_pipeline = diffuser_pipeline.to(device)

output = diffuser_pipeline(speech_data)
plt.imshow(output.images[0])

prompt = "__animal__ sitting on a __object__ wearing a __clothing__"

dog
cat
mouse

chair
sofa
bench

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="wildcard_stable_diffusion",

    torch_dtype=torch.float16,
)
prompt = "__animal__ sitting on a __object__ wearing a __clothing__"
out = pipe(
    prompt,
    wildcard_option_dict={
        "clothing":["hat", "shirt", "scarf", "beret"]
    },
    wildcard_files=["object.txt", "animal.txt"],
    num_prompt_samples=1
)

import torch as th
import numpy as np
import torchvision.utils as tvu

from diffusers import DiffusionPipeline

import argparse

parser = argparse.ArgumentParser()
parser.add_argument("--prompt", type=str, default="mystical trees | A magical pond | dark",
                    help="use '|' as the delimiter to compose separate sentences.")
parser.add_argument("--steps", type=int, default=50)
parser.add_argument("--scale", type=float, default=7.5)
parser.add_argument("--weights", type=str, default="7.5 | 7.5 | -7.5")
parser.add_argument("--seed", type=int, default=2)
parser.add_argument("--model_path", type=str, default="CompVis/stable-diffusion-v1-4")
parser.add_argument("--num_images", type=int, default=1)
args = parser.parse_args()

has_cuda = th.cuda.is_available()
device = th.device('cpu' if not has_cuda else 'cuda')

prompt = args.prompt
scale = args.scale
steps = args.steps

pipe = DiffusionPipeline.from_pretrained(
    args.model_path,
    custom_pipeline="composable_stable_diffusion",
).to(device)

pipe.safety_checker = None

images = []
generator = th.Generator("cuda").manual_seed(args.seed)
for i in range(args.num_images):
    image = pipe(prompt, guidance_scale=scale, num_inference_steps=steps,
                 weights=args.weights, generator=generator).images[0]
    images.append(th.from_numpy(np.array(image)).permute(2, 0, 1) / 255.)
grid = tvu.make_grid(th.stack(images, dim=0), nrow=4, padding=0)
tvu.save_image(grid, f'{prompt}_{args.weights}' + '.png')

import requests
from PIL import Image
from io import BytesIO
import torch
import os
from diffusers import DiffusionPipeline, DDIMScheduler
has_cuda = torch.cuda.is_available()
device = torch.device('cpu' if not has_cuda else 'cuda')
pipe = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
        safety_checker=None,
    custom_pipeline="imagic_stable_diffusion",
    scheduler = DDIMScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False)
).to(device)
generator = torch.Generator("cuda").manual_seed(0)
seed = 0
prompt = "A photo of Barack Obama smiling with a big grin"
url = 'https://www.dropbox.com/s/6tlwzr73jd1r9yk/obama.png?dl=1'
response = requests.get(url)
init_image = Image.open(BytesIO(response.content)).convert("RGB")
init_image = init_image.resize((512, 512))
res = pipe.train(
    prompt,
    image=init_image,
    generator=generator)
res = pipe(alpha=1, guidance_scale=7.5, num_inference_steps=50)
os.makedirs("imagic", exist_ok=True)
image = res.images[0]
image.save('./imagic/imagic_image_alpha_1.png')
res = pipe(alpha=1.5, guidance_scale=7.5, num_inference_steps=50)
image = res.images[0]
image.save('./imagic/imagic_image_alpha_1_5.png')
res = pipe(alpha=2, guidance_scale=7.5, num_inference_steps=50)
image = res.images[0]
image.save('./imagic/imagic_image_alpha_2.png')

import torch as th
import numpy as np
from diffusers import DiffusionPipeline

has_cuda = th.cuda.is_available()
device = th.device('cpu' if not has_cuda else 'cuda')

pipe = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="seed_resize_stable_diffusion"
).to(device)

def dummy(images, **kwargs):
    return images, False

pipe.safety_checker = dummy


images = []
th.manual_seed(0)
generator = th.Generator("cuda").manual_seed(0)

seed = 0
prompt = "A painting of a futuristic cop"

width = 512
height = 512

res = pipe(
    prompt,
    guidance_scale=7.5,
    num_inference_steps=50,
    height=height,
    width=width,
    generator=generator)
image = res.images[0]
image.save('./seed_resize/seed_resize_{w}_{h}_image.png'.format(w=width, h=height))


th.manual_seed(0)
generator = th.Generator("cuda").manual_seed(0)

pipe = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="/home/mark/open_source/diffusers/examples/community/"
).to(device)

width = 512
height = 592

res = pipe(
    prompt,
    guidance_scale=7.5,
    num_inference_steps=50,
    height=height,
    width=width,
    generator=generator)
image = res.images[0]
image.save('./seed_resize/seed_resize_{w}_{h}_image.png'.format(w=width, h=height))

pipe_compare = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="/home/mark/open_source/diffusers/examples/community/"
).to(device)

res = pipe_compare(
    prompt,
    guidance_scale=7.5,
    num_inference_steps=50,
    height=height,
    width=width,
    generator=generator
)

image = res.images[0]
image.save('./seed_resize/seed_resize_{w}_{h}_image_compare.png'.format(w=width, h=height))

from PIL import Image

import torch

from diffusers import DiffusionPipeline
from transformers import (
    pipeline,
    MBart50TokenizerFast,
    MBartForConditionalGeneration,
)
device = "cuda" if torch.cuda.is_available() else "cpu"
device_dict = {"cuda": 0, "cpu": -1}

# helper function taken from: https://huggingface.co/blog/stable_diffusion
def image_grid(imgs, rows, cols):
    assert len(imgs) == rows*cols

    w, h = imgs[0].size
    grid = Image.new('RGB', size=(cols*w, rows*h))
    grid_w, grid_h = grid.size

    for i, img in enumerate(imgs):
        grid.paste(img, box=(i%cols*w, i//cols*h))
    return grid

# Add language detection pipeline
language_detection_model_ckpt = "papluca/xlm-roberta-base-language-detection"
language_detection_pipeline = pipeline("text-classification",
                                       model=language_detection_model_ckpt,
                                       device=device_dict[device])

# Add model for language translation
trans_tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-many-to-one-mmt")
trans_model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-many-to-one-mmt").to(device)

diffuser_pipeline = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="multilingual_stable_diffusion",
    detection_pipeline=language_detection_pipeline,
    translation_model=trans_model,
    translation_tokenizer=trans_tokenizer,

    torch_dtype=torch.float16,
)

diffuser_pipeline.enable_attention_slicing()
diffuser_pipeline = diffuser_pipeline.to(device)

prompt = ["a photograph of an astronaut riding a horse",
          "Una casa en la playa",
          "Ein Hund, der Orange isst",
          "Un restaurant parisien"]

output = diffuser_pipeline(prompt)

images = output.images

grid = image_grid(images, rows=2, cols=2)

from PIL import Image

import torch

from transformers import AutoModel, AutoTokenizer

from diffusers import DiffusionPipeline

if __name__ == "__main__":
    device = "cuda"

    lm_model_id = "xlm-roberta-large"
    token_max_length = 77

    text_encoder = AutoModel.from_pretrained(lm_model_id)
    tokenizer = AutoTokenizer.from_pretrained(lm_model_id, model_max_length=token_max_length, use_fast=False)

    tensor_norm = torch.Tensor([[43.8203],[28.3668],[27.9345],[28.0084],[28.2958],[28.2576],[28.3373],[28.2695],[28.4097],[28.2790],[28.2825],[28.2807],[28.2775],[28.2708],[28.2682],[28.2624],[28.2589],[28.2611],[28.2616],[28.2639],[28.2613],[28.2566],[28.2615],[28.2665],[28.2799],[28.2885],[28.2852],[28.2863],[28.2780],[28.2818],[28.2764],[28.2532],[28.2412],[28.2336],[28.2514],[28.2734],[28.2763],[28.2977],[28.2971],[28.2948],[28.2818],[28.2676],[28.2831],[28.2890],[28.2979],[28.2999],[28.3117],[28.3363],[28.3554],[28.3626],[28.3589],[28.3597],[28.3543],[28.3660],[28.3731],[28.3717],[28.3812],[28.3753],[28.3810],[28.3777],[28.3693],[28.3713],[28.3670],[28.3691],[28.3679],[28.3624],[28.3703],[28.3703],[28.3720],[28.3594],[28.3576],[28.3562],[28.3438],[28.3376],[28.3389],[28.3433],[28.3191]])

    pipeline = DiffusionPipeline.from_pretrained(
        "runwayml/stable-diffusion-v1-5",
        text_encoder=text_encoder,
        tokenizer=tokenizer,
        custom_pipeline="gluegen"
    ).to(device)
    pipeline.load_language_adapter("gluenet_French_clip_overnorm_over3_noln.ckpt", num_token=token_max_length, dim=1024, dim_out=768, tensor_norm=tensor_norm)

    prompt = "une voiture sur la plage"

    generator = torch.Generator(device=device).manual_seed(42)
    image = pipeline(prompt, generator=generator).images[0]
    image.save("gluegen_output_fr.png")

import PIL
import torch

from diffusers import DiffusionPipeline

image_path = "./path-to-image.png"
inner_image_path = "./path-to-inner-image.png"
mask_path = "./path-to-mask.png"

init_image = PIL.Image.open(image_path).convert("RGB").resize((512, 512))
inner_image = PIL.Image.open(inner_image_path).convert("RGBA").resize((512, 512))
mask_image = PIL.Image.open(mask_path).convert("RGB").resize((512, 512))

pipe = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-inpainting",
    custom_pipeline="img2img_inpainting",

    torch_dtype=torch.float16
)
pipe = pipe.to("cuda")

prompt = "Your prompt here!"
image = pipe(prompt=prompt, image=init_image, inner_image=inner_image, mask_image=mask_image).images[0]

from transformers import CLIPSegProcessor, CLIPSegForImageSegmentation
from diffusers import DiffusionPipeline

from PIL import Image
import requests

processor = CLIPSegProcessor.from_pretrained("CIDAS/clipseg-rd64-refined")
model = CLIPSegForImageSegmentation.from_pretrained("CIDAS/clipseg-rd64-refined")

pipe = DiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-inpainting",
    custom_pipeline="text_inpainting",
    segmentation_model=model,
    segmentation_processor=processor
)
pipe = pipe.to("cuda")


url = "https://github.com/timojl/clipseg/blob/master/example_image.jpg?raw=true"
image = Image.open(requests.get(url, stream=True).raw).resize((512, 512))
text = "a glass"  # will mask out this text
prompt = "a cup"  # the masked out region will be replaced with this

image = pipe(image=image, text=text, prompt=prompt).images[0]

from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained("google/ddpm-cifar10-32", custom_pipeline="bit_diffusion")
image = pipe().images[0]

pip install k-diffusion

from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", custom_pipeline="sd_text2img_k_diffusion")
pipe = pipe.to("cuda")

prompt = "an astronaut riding a horse on mars"
pipe.set_scheduler("sample_heun")
generator = torch.Generator(device="cuda").manual_seed(seed)
image = pipe(prompt, generator=generator, num_inference_steps=20).images[0]

image.save("./astronaut_heun_k_diffusion.png")

from diffusers import DiffusionPipeline, EulerDiscreteScheduler

seed = 33

pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")

generator = torch.Generator(device="cuda").manual_seed(seed)
image = pipe(prompt, generator=generator, num_inference_steps=50).images[0]

from diffusers import DiffusionPipeline, EulerDiscreteScheduler

seed = 33

pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", custom_pipeline="sd_text2img_k_diffusion")
pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")

pipe.set_scheduler("sample_euler")
generator = torch.Generator(device="cuda").manual_seed(seed)
image = pipe(prompt, generator=generator, num_inference_steps=50).images[0]

from diffusers import DiffusionPipeline

#Return a CheckpointMergerPipeline class that allows you to merge checkpoints.
#The checkpoint passed here is ignored. But still pass one of the checkpoints you plan to
#merge for convenience
pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", custom_pipeline="checkpoint_merger")

#There are multiple possible scenarios:
#The pipeline with the merged checkpoints is returned in all the scenarios

#Compatible checkpoints a.k.a matched model_index.json files. Ignores the meta attributes in model_index.json during comparison.( attrs with _ as prefix )
merged_pipe = pipe.merge(["CompVis/stable-diffusion-v1-4","CompVis/stable-diffusion-v1-2"], interp = "sigmoid", alpha = 0.4)

#Incompatible checkpoints in model_index.json but merge might be possible. Use force = True to ignore model_index.json compatibility
merged_pipe_1 = pipe.merge(["CompVis/stable-diffusion-v1-4","hakurei/waifu-diffusion"], force = True, interp = "sigmoid", alpha = 0.4)

#Three checkpoint merging. Only "add_difference" method actually works on all three checkpoints. Using any other options will ignore the 3rd checkpoint.
merged_pipe_2 = pipe.merge(["CompVis/stable-diffusion-v1-4","hakurei/waifu-diffusion","prompthero/openjourney"], force = True, interp = "add_difference", alpha = 0.4)

prompt = "An astronaut riding a horse on Mars"

image = merged_pipe(prompt).images[0]

from diffusers import DiffusionPipeline
import matplotlib.pyplot as plt

pipe = DiffusionPipeline.from_pretrained('CompVis/stable-diffusion-v1-4', custom_pipeline='suvadityamuk/StableDiffusionComparison')
pipe.enable_attention_slicing()
pipe = pipe.to('cuda')
prompt = "an astronaut riding a horse on mars"
output = pipe(prompt)

plt.subplots(2,2,1)
plt.imshow(output.images[0])
plt.title('Stable Diffusion v1.1')
plt.axis('off')
plt.subplots(2,2,2)
plt.imshow(output.images[1])
plt.title('Stable Diffusion v1.2')
plt.axis('off')
plt.subplots(2,2,3)
plt.imshow(output.images[2])
plt.title('Stable Diffusion v1.3')
plt.axis('off')
plt.subplots(2,2,4)
plt.imshow(output.images[3])
plt.title('Stable Diffusion v1.4')
plt.axis('off')

plt.show()

from diffusers import DiffusionPipeline, DDIMScheduler
from PIL import Image

pipe = DiffusionPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="magic_mix",
    scheduler = DDIMScheduler.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="scheduler"),
).to('cuda')

img = Image.open('phone.jpg')
mix_img = pipe(
    img,
    prompt = 'bed',
    kmin = 0.3,
    kmax = 0.5,
    mix_factor = 0.5,
    )
mix_img.save('phone_bed_mix.jpg')

import torch
from diffusers import DiffusionPipeline

device = torch.device("cpu" if not torch.cuda.is_available() else "cuda")

pipeline = DiffusionPipeline.from_pretrained(
    "kakaobrain/karlo-v1-alpha",
    torch_dtype=torch.float16,
    custom_pipeline="stable_unclip",
    decoder_pipe_kwargs=dict(
        image_encoder=None,
    ),
)
pipeline.to(device)

prompt = "a shiba inu wearing a beret and black turtleneck"
random_generator = torch.Generator(device=device).manual_seed(1000)
output = pipeline(
    prompt=prompt,
    width=512,
    height=512,
    generator=random_generator,
    prior_guidance_scale=4,
    prior_num_inference_steps=25,
    decoder_guidance_scale=8,
    decoder_num_inference_steps=50,
)

image = output.images[0]
image.save("./shiba-inu.jpg")

# debug

# `pipeline.decoder_pipe` is a regular StableDiffusionImageVariationPipeline instance.
# It is used to convert clip image embedding to latents, then fed into VAE decoder.
print(pipeline.decoder_pipe.__class__)
# 

# this pipeline only use prior module in "kakaobrain/karlo-v1-alpha"
# It is used to convert clip text embedding to clip image embedding.
print(pipeline)
# StableUnCLIPPipeline {
#   "_class_name": "StableUnCLIPPipeline",
#   "_diffusers_version": "0.12.0.dev0",
#   "prior": [
#     "diffusers",
#     "PriorTransformer"
#   ],
#   "prior_scheduler": [
#     "diffusers",
#     "UnCLIPScheduler"
#   ],
#   "text_encoder": [
#     "transformers",
#     "CLIPTextModelWithProjection"
#   ],
#   "tokenizer": [
#     "transformers",
#     "CLIPTokenizer"
#   ]
# }

# pipeline.prior_scheduler is the scheduler used for prior in UnCLIP.
print(pipeline.prior_scheduler)
# UnCLIPScheduler {
#   "_class_name": "UnCLIPScheduler",
#   "_diffusers_version": "0.12.0.dev0",
#   "clip_sample": true,
#   "clip_sample_range": 5.0,
#   "num_train_timesteps": 1000,
#   "prediction_type": "sample",
#   "variance_type": "fixed_small_log"
# }

i

[Content truncated...]