shuttleai/shuttle-3-diffusion

Instalación y uso básico con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained(
    "shuttleai/shuttle-3-diffusion",
    dtype=torch.bfloat16,
    device_map="cuda"
)

prompt = "Venus floating market at dawn, fantasy digital art, highly detailed, atmospheric lighting with film-like light leaks, impressive background, studio photo style, cinematic, intricate details."
image = pipe(prompt).images[0]

Ejemplo completo con configuración de tamaño, guidance y pasos:

pip install -U diffusers

import torch
from diffusers import DiffusionPipeline

# Load the diffusion pipeline from a pretrained model, using bfloat16 for tensor types.
pipe = DiffusionPipeline.from_pretrained(
    "shuttleai/shuttle-3-diffusion",
    torch_dtype=torch.bfloat16
).to("cuda")

# Uncomment the following line to save VRAM by offloading the model to CPU if needed.
# pipe.enable_model_cpu_offload()

# Set your prompt for image generation.
prompt = "A cat holding a sign that says hello world"

# Generate the image using the diffusion pipeline.
image = pipe(
    prompt,
    height=1024,
    width=1024,
    guidance_scale=3.5,
    num_inference_steps=4,
    max_sequence_length=256,
    # generator=torch.Generator("cpu").manual_seed(0)
).images[0]

# Save the generated image.
image.save("shuttle.png")

También puede ejecutarse mediante la API de ShuttleAI o en ComfyUI usando el archivo Safetensors del modelo.