How to use anvilarth/sdxl-t5-encoder with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("anvilarth/sdxl-t5-encoder", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
Stable Diffusion XL (SDXL) fine-tuned with a umT5-XXL text encoder to boost compositional prompt understanding and reduce mis-interpretations.
Base model
