Sana How to use Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers with Sana:
# Load the model and infer image from text
import torch
from app.sana_pipeline import SanaPipeline
from torchvision.utils import save_image
sana = SanaPipeline("configs/sana_config/1024ms/Sana_1600M_img1024.yaml")
sana.from_pretrained("hf://Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers")
image = sana(
prompt='a cyberpunk cat with a neon sign that says "Sana"',
height=1024,
width=1024,
guidance_scale=5.0,
pag_guidance_scale=2.0,
num_inference_steps=18,
) Diffusers How to use Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Efficient-Large-Model/SANA1.5_4.8B_1024px_diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0] 
