YOSO (YOSO-LoRA) - You Only Sample Once

import torch
from diffusers import DiffusionPipeline, LCMScheduler

# Inferencia de un solo paso
pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipeline = pipeline.to('cuda')
pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
generator = torch.manual_seed(318)
steps = 1
bs = 1
latents = ... # Tal vez algunos códigos latentes de imágenes reales o generación de SD
latent_mean = latent.mean(dim=0)
init_latent = latent_mean.repeat(bs, 1, 1, 1) + latents.std() * torch.randn_like(latents)
noise = torch.randn([bs, 4, 64, 64])
input_latent = pipeline.scheduler.add_noise(init_latent, noise, T)
imgs = pipeline(
    prompt="A photo of a dog",
    num_inference_steps=steps,
    num_images_per_prompt=1,
    generator=generator,
    guidance_scale=1.5,
    latents=input_latent,
)[0]

# Inferencia simple sin inicialización informativa
pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16)
pipeline = pipeline.to('cuda')
pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
generator = torch.manual_seed(318)
steps = 1
imgs = pipeline(
    prompt="A photo of a corgi in forest, highly detailed, 8k, XT3.",
    num_inference_steps=1,
    num_images_per_prompt=1,
    generator=generator,
    guidance_scale=1.,
)[0]

# Inferencia de dos pasos
pipeline = DiffusionPipeline.from_pretrained("stablediffusionapi/realistic-vision-v51", torch_dtype=torch.float16)
pipeline = pipeline.to('cuda')
pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config)
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
generator = torch.manual_seed(318)
steps = 2
imgs= pipeline(
    prompt="A photo of a man, XT3",
    num_inference_steps=steps,
    num_images_per_prompt=1,
    generator=generator,
    guidance_scale=1.5,
)[0]

# Uso con nuevos modelos base y solucionadores avanzados
from diffusers import DPMSolverMultistepScheduler
pipeline = DiffusionPipeline.from_pretrained("stablediffusionapi/realistic-vision-v51", torch_dtype=torch.float16)
pipeline = pipeline.to('cuda')
pipeline.load_lora_weights('Luo-Yihong/yoso_sd1.5_lora')
pipeline.scheduler = DPMSolverMultistepScheduler.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="scheduler")
generator = torch.manual_seed(323)
steps = 2
imgs= pipeline(
    prompt="A photo of a girl, XT3",
    num_inference_steps=steps,
    num_images_per_prompt=1,
    generator=generator,
    guidance_scale=1.5,
)[0]

# Prueba con diferentes solucionadores
img_list = []
for age in [2, 20, 30, 50, 60, 80]:
    imgs = pipeline(
        prompt=f"A photo of a cute girl, {age} yr old, XT3",
        num_inference_steps=steps,
        num_images_per_prompt=1,
        generator=generator,
        guidance_scale=1.1,
    )[0]
    img_list.append(imgs[0])
make_image_grid(img_list, rows=1, cols=len(img_list))