How to use SceneWorks/Sana_Sprint_1.6B_1024px_mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Sana_Sprint_1.6B_1024px_mlx SceneWorks/Sana_Sprint_1.6B_1024px_mlx
How to use SceneWorks/Sana_Sprint_1.6B_1024px_mlx 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://SceneWorks/Sana_Sprint_1.6B_1024px_mlx") 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, )
