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

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(
    "CompVis/stable-diffusion-v1-4",
    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)

# 이미지 로컬에 저장하기
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",
    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(
    "CompVis/stable-diffusion-v1-4",
    custom_pipeline="stable_diffusion_mega",
    torch_dtype=torch.float16,
)
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])