How to use Efficient-Large-Model/SANA-WM_bidirectional-diffusers-refiner 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/SANA-WM_bidirectional-diffusers-refiner", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
https://huggingface.co/Efficient-Large-Model/SANA-WM_bidirectional-diffusers-refiner/resolve/main/text_encoder/processor_config.json
hf download hf://Efficient-Large-Model/SANA-WM_bidirectional-diffusers-refiner/text_encoder/processor_config.json
curl -L -o processor_config.json https://huggingface.co/Efficient-Large-Model/SANA-WM_bidirectional-diffusers-refiner/resolve/main/text_encoder/processor_config.json
