huanzi05/stable-diffusion-2-1-base

Instalación y uso con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained(
    "huanzi05/stable-diffusion-2-1-base",
    dtype=torch.bfloat16,
    device_map="cuda"
)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

Ejemplo alternativo con scheduler Euler:

pip install diffusers transformers accelerate scipy safetensors

from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
import torch

model_id = "stabilityai/stable-diffusion-2-1-base"
scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder="scheduler")
pipe = StableDiffusionPipeline.from_pretrained(
    model_id,
    scheduler=scheduler,
    torch_dtype=torch.float16
)
pipe = pipe.to("cuda")

prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]
image.save("astronaut_rides_horse.png")

Se recomienda instalar xformers para atención más eficiente en memoria. En GPUs con poca VRAM, puede usarse pipe.enable_attention_slicing() después de mover el pipeline a CUDA, con menor consumo de memoria a cambio de velocidad.