How to use BiliSakura/MiniT2I-diffusers with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BiliSakura/MiniT2I-diffusers", dtype=torch.bfloat16, device_map="cuda") prompt = "A lonely astronaut standing on a quiet beach under two moons." image = pipe(prompt).images[0]
https://huggingface.co/BiliSakura/MiniT2I-diffusers/resolve/main/MiniT2I-L-16/text_encoder/tokenizer.json
hf download hf://BiliSakura/MiniT2I-diffusers/MiniT2I-L-16/text_encoder/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/BiliSakura/MiniT2I-diffusers/resolve/main/MiniT2I-L-16/text_encoder/tokenizer.json
