How to use MoritzAMLLaura/trained-sd3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MoritzAMLLaura/trained-sd3", dtype=torch.bfloat16, device_map="cuda") prompt = "a photo of sks dog" image = pipe(prompt).images[0]
https://huggingface.co/MoritzAMLLaura/trained-sd3/resolve/main/tokenizer_2/merges.txt
hf download hf://MoritzAMLLaura/trained-sd3/tokenizer_2/merges.txt
curl -L -o merges.txt https://huggingface.co/MoritzAMLLaura/trained-sd3/resolve/main/tokenizer_2/merges.txt
