How to use aa-studio/aa_studio_data with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("aa-studio/aa_studio_data", 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/aa-studio/aa_studio_data/resolve/07e165bcf451b7c06e1d39ffecf3d1fa5937cfb7/ComfyUI/__pycache__/cuda_malloc.cpython-310.pyc
hf download hf://aa-studio/aa_studio_data@07e165bcf451b7c06e1d39ffecf3d1fa5937cfb7/ComfyUI/__pycache__/cuda_malloc.cpython-310.pyc
curl -L -o cuda_malloc.cpython-310.pyc https://huggingface.co/aa-studio/aa_studio_data/resolve/07e165bcf451b7c06e1d39ffecf3d1fa5937cfb7/ComfyUI/__pycache__/cuda_malloc.cpython-310.pyc
