How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("martyn/sdxl-evolved-aesthetic", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

SDXL Evolved - Aesthetic

Images generated with no prompt.

Generation settings

Best results with: Euler with trailing(SGMUniform) at 8+, Guidance scale 1. Similar to SDXL Lightning

Details

Created with https://github.com/255BITS/diffusion-evolver

Evolved for 20 cycles towards more aesthetic images.

Downloads last month
6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including martyn/sdxl-evolved-aesthetic