SDXL Flash

Introducing the new fast model SDXL Flash, we learned that all fast XL models work fast, but the quality decreases, and we also made a fast model, but it is not as fast as LCM, Turbo, Lightning and Hyper, but the quality is higher. Below you will see the study with steps and cfg.
Steps and CFG (Guidance)

Optimal settings
Steps: 6-9
CFG Scale: 2.5-3.5
Sampler: DPM++ SDE
Description
--> Work with LoRA <--
Trigger word: <lora:sdxlFlash_lora:0.55>
Optimal LoRA multiplier: 0.45-0.6 (the best - 0.55)
Optimal base model: FluentlyXL v4
fast sdxl
base model
animals
people
photorealistic
art
realism
lightning
flash
turbo
sdxl 1,0
lcm
sdxl-flash
lora
basemodel
Details
Downloads
148
Platform
CivitAI
Platform Status
Available
Created
6/14/2024
Updated
1/10/2026
Deleted
-
Files
sdxlFlash_lora.safetensors
Mirrors
CivitAI (1 mirrors)