A very basic, minimalistic workflow for Shuttle 3.1 Aesthetic.
For generating images with Shuttle 3.1 Aesthetic
Shuttle 3.1 Aesthetic is a text-to-image AI model designed to create detailed and aesthetic images from textual prompts in just 4 to 6 steps. It offers enhanced performance in image quality, typography, understanding complex prompts, and resource efficiency.
bfloat16 checkpoint (24GB): Download here
fp8 checkpoint (12GB): Download here
Place either of them in /models/diffusion_models/
Enjoy!
Description
This workflow contains the same nodes as the previous version, with the addition of 4 lora nodes that will extract the triggerowords from lora, print them in the workflow and save them in a .json file which you can use to auto-trigger loras.
Workflow can be used for Shuttle 3.1, Flux Dev and Flux Schnell.


