How to use schrum2/MarioDiffusion-MiniLM-multiple-negative0 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("schrum2/MarioDiffusion-MiniLM-multiple-negative0", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
8f07459
1
{"best_epoch": 395, "best_val_loss": 0.20986390858888626, "best_caption_score": 0.8126663773148145}
