List your company

Consistent Text-to-Image Generation on ConsiStory+ (test)

0.9074CLIP-TVanilla SDXL
0.7548320.7944410.834050.873659Oct 16, 2025Nov 3, 2025Nov 21, 2025Dec 9, 2025Dec 27, 2025Jan 14, 2026Feb 1, 2026

Evaluation results

MethodLinks
Vanilla SDXLSteps=50, Memory (GB)=16.04, Inference Time (s)=13.0892026.020.90740.81650.5292—————
DeCorStoryBase Model=SDXL, Train-Free=true, Steps=50, Memory (GB)=18.72, Inference Time (s)=23.35212026.020.90010.91340.1922—————
SDeC+ConsiStoryBase model=SDXL, PE=true, Steps=502025.100.89670.8744—0.25420.41550.672715.56
SDeCBase model=SDXL, PE=true, Steps=502025.100.89460.8655—0.25890.36750.611512.14
1Prompt1StoryBase Model=SDXL, Train-Free=true, Steps=50, Memory (GB)=18.7, Inference Time (s)=23.20882026.020.89420.91170.1993—————
ConsiStoryBase model=SDXL, PE=false, Steps=502025.100.89420.8604—0.27290.420702715.58
1P1SBase model=SDXL, PE=false, Steps=502025.100.88830.8798—0.22380.29550.12213.1
StoryDiffusionBase Model=SDXL, Train-Free=true, Steps=50, Memory (GB)=45.61, Inference Time (s)=25.69282026.020.88770.87550.3212—————
Baseline (SDXL)Base model=SDXL, PE=false, Steps=502025.100.88650.8558—0.27780.38610910.72
PhotoMakerBase model=SDXL, PE=false, Steps=502025.100.88120.8545—0.28080.3957099.74
ConsiStoryBase Model=SDXL, Train-Free=true, Steps=50, Memory (GB)=34.55, Inference Time (s)=34.58942026.020.87690.87370.3188—————
PhotoMakerBase Model=SDXL, Train-Free=false, Steps=50, Memory (GB)=23.79, Inference Time (s)=18.02592026.020.86510.84650.3996—————
1P1S w/o IPCABase model=SDXL, PE=false, Steps=502025.100.86370.8617—0.26820.33380.11910.74
StoryDiffusionBase model=SDXL, PE=false, Steps=502025.100.85780.8502—0.31970.421402438.44
Textual InversionBase model=SDXL, PE=false, Steps=402025.100.85570.8437—0.30660.391901014
IP-AdapterBase Model=SDXL, Train-Free=false, Steps=30, Memory (GB)=19.39, Inference Time (s)=13.45942026.020.84580.94290.1462—————
Naive Prompt Reweighting (NPR)Base Model=SDXL, Train-Free=true, Steps=50, Memory (GB)=16.04, Inference Time (s)=17.24132026.020.84110.89160.2548—————
Textual InversionBase Model=SD1.5, Train-Free=false, Steps=40, Memory (GB)=32.94, Inference Time (s)=282.5072026.020.83780.82290.4268—————
Vanilla SD1.5Steps=50, Memory (GB)=4.73, Inference Time (s)=2.46572026.020.83530.74740.5873—————
Baseline (SD1.5)Base model=SD1.5, PE=false, Steps=502025.100.83240.8071—0.41180.4673023.18
BLIP-DiffusionBase model=SD1.5, PE=false, Steps=262025.100.81870.8522—0.28510.3957013.54
The Chosen OneBase Model=SDXL, Train-Free=false, Steps=35, Memory (GB)=10.93, Inference Time (s)=11.20732026.020.76140.78310.4929—————
BLIP-DiffusionBase Model=SD1.5, Train-Free=false, Steps=26, Memory (GB)=7.75, Inference Time (s)=1.92842026.020.76070.88630.283—————