icon-logo
SDXL Turbo-LoRA-Stable Diffusion XL
LoRA
coll-num13
look-num45

v1

share
selectCommunity
Model Permissions:
prompt-imgEveryone Can See The Model
prompt-imgAnyone Can Use The Model
prompt-imgCommercial Use Permitted
S
srht8
uploader
Details
Category
STYLE
Type
LoRA
Base Model
SDXL 1.0
Best With
SDXL (1.0)
Uploaded
December 5.2023
Added
13
Runs
45
Security
Verified

v1: 128 dim

v1-64dim: half dimension, similar quality

v1-16dim: 94MB, similar quality(but different results in some prompts... I suggest the 128 dim or 64 dim version, but if you have a gpu with 6 GB vram try this version)

LoRA based on new sdxl turbo, you can use the TURBO with any stable diffusion xl checkpointfew seconds = 1 image(3 seconds with a nvidia rtx 3060 12 GB with 1024x768 resolution)

Tested on webui 1111 v1.6.0-2-g4afaaf8a

Tested on ComfyUI v1754 [777f6b15]: workflow

(new version of workflow November 30, 2023 remove strange violet fog, keep sgm_uniform as scheduler and you can use every sampler)

1-Select your favourite stable diffusion xl checkpoint

2-Download this LoRA, use my workflow for ComfyUI or any workflow with LoRA loader

For webui 1111 write in the prompt <lora:sd_xl_turbo_lora_v1:1>

3-Sampling method on webui 1111: LCM(install animatediff extension if you don't see it in sampling list)

Sampling method on ComfyUI: all, with the workflow of November 30, 2023

4-CFG Scale: from 1 to 2

5-Sampling steps: 4

Show More
Gallery
share
share