FLUX-style Lora for SDXL - v0.2
Powiązane słowa kluczowe i tagi
Zalecane podpowiedzi
flux-style
Zalecane negatywne podpowiedzi
low quality, deformed, boring
Zalecane parametry
samplers
DDPM
steps
14 - 18
cfg
1.2 - 2
clip skip
2
resolution
720x1280
vae
sdxl_vae.safetensors
other models
aidmaFluxStyleXL-v0.2 (6c2a2b2c3859), aidmaBokehmachine-V0.1 (7a79c5da33d1), aidma-Image Upgrader-v0.1 (e4be4bfcf4dc), ForRealXL-V0.5 (6f228e128a), aidmaGlitchStyle-v0.1 (d32a5d50652b), ForArtisticXL-v0.1 (34cd71e533), CBS_novuschroma37 style_b (6e1eab82e245)
Zalecane parametry wysokiej rozdzielczości
upscaler
4x_NMKD-Siax_200k, SwinIR_4x
upscale
1.5
steps
14
denoising strength
0.16
Wskazówki
Start setting the parameter value between 0.5 and 1.0, preferably starting at 0.5.
Try generating images both with and without the 'flux-style' trigger to see varied results.
If using version 0.1 of the model, be aware that a different activation trigger is required.
Najważniejsze informacje o wersji
trained with 100 images
fixed the Trigger 🫠
fixed a bug with the lora name
fixed a training image duplicate
Sponsorzy twórcy
for whatever reason you want to show me appreciation, you can: ❤️Ko-Fi❤️
Hello ♥
for whatever reason you want to show me appreciation, you can: ❤️Ko-Fi❤️

Made around 5-6k Images with Flux the last 3 days and made this Lora with 50 (100 with v0.2) of my favorite images.
Will train way more in the next versions.
FLUX is way better than this lora (with text), but sometimes you get a cool result with good text.
Settings
0.5 - 1.0
start with 0.5
try with and without Trigger
Trigger
flux-style
careful, if you use V0.1 there is an other trigger to activate
Hope you get a lot of beautiful results ♥
Szczegóły modelu
Typ modelu
LORA
Model bazowy
SDXL 1.0
Wersja modelu
v0.2
Hash modelu
e691239869
Wytrenowane słowa
flux-style
Twórca
Dyskusja
Proszę się log in, aby dodać komentarz.














