Sign In

In Memory of Leonardo

0

Early Access

Not recently loaded

Download

1 variant available

bf16 SafeTensor

X4LSFUMATO_krea2_CodexX.safetensors

BF16, good balance • 223.83 MB

Verified:

Type
LoRA
Stats

1

0

Reviews
Published

Oct 21, 2026

Base Model

Krea 2

Training
Steps: 720
Epochs: 10
Usage Tips
Strength: 1
Hash
AutoV2
42A8C7E98D
Trigger Words
X4LSFUMATO
20261021180706-66666-krea2-krea2TurboOfficialComfy_krea2TurboFp8-text2img_00000.png

In Memory of Leonardo

A style LoRA built entirely from my own urban exploration photography, years of abandoned villas, chapels, workshops and forgotten rooms, condensed into one look.

The name is a quiet tribute. Sfumato, the soft transition from light into shadow, is what defines these places for me: a single beam through a broken window, dust in the air, and everything else slowly dissolving into darkness.

Trigger word

X4LSFUMATO


Style prefixes (from the three training sets)

X4LSFUMATO, dark cinematic color grading, deep shadows, heavy vignette
X4LSFUMATO, warm muted film tones, soft faded colors
X4LSFUMATO, natural warm light, documentary photo

- Base model: Krea 2 Turbo (trained on Krea 2 Raw)

- Strength: 1.0 – 1.4, up to 2.5 for an extreme painterly look

Tips

- Keep prompts short and factual: the place, the objects, where the light comes from, the camera angle. Long style or lighting descriptions override the LoRA.

- One light source works best. A single beam onto the main subject with the rest of the room falling into shadow is exactly what it was trained on.

- For the punchy dark look, add: teal blue shadows and warm orange highlights, high local contrast

- It also adds decay to scenes that are not abandoned at all, but stays subtle when the prompt clearly describes an active place.

Known limitations

- Torn fabric (curtains, tarps) sometimes gets unnaturally round holes.

- On surfaces like signs or license plates the trigger word can show up as text. Avoid those in the prompt or retry with another seed.

Dataset: 72 of my own photographs, captioned by hand and with a local vision model, rank 32.

A MOSS version is planned.