Sign In
homemodelsimagesvideos3D Modelsarticlescomicschallengesupdatesshop

Flash Photo SDXL

30.4k

Updated: Oct 5, 2024

conceptdarklightingphotographyphotorealismflash photo

Download

1 variant available

SafeTensor

908.66 KB

Verified:

Type
LoRA
Stats

2,867

30.3K

6.1K

Reviews

(219)

Published

Oct 29, 2023

Base Model

SDXL 1.0

Training
Epochs: 60
Usage Tips
Clip Skip: 1
Hash
AutoV2
C706E3F283
Trigger Words
very dark focused flash photo
default creator card background decoration
Uploads - 18

18

Downloads - 24976

25K

Generations - 311677

311.7K

License:

CreativeML Open RAIL++-MAddendum
35816-2-very dark focused flash photo of found footage of a werewolf with sharp claws staring from behind the window of a dark bedroom a.png

1 MB iA3 Network

*UPDATE*: v6 is trained with Debiased Estimation Loss on the dev branch of kohya_ss sd-scripts. This makes image structure more coherent and have better color. If you train a model with Debiased Estimation Loss, you shouldn't need to use Min-SNR gamma or Color Aug as it does both better.

Prompt format: very dark focused flash photo of <subject> at night, wide angle, black background

I recommend using DPM++ 3M Exponential/Karras with 40-100 steps. Use the refiner at 0.8 for photorealism.