Sign In

Grunge

50

289

48

19

Updated: Oct 3, 2024

styleoldgrungerustdirtworn

Verified:

SafeTensor

Type

LoRA

Stats

289

48

241

Reviews

Published

Oct 3, 2024

Base Model

Flux.1 D

Training

Steps: 3,000

Trigger Words

GRUNGE

Hash

AutoV2
FBC3FDC006
default creator card background decoration
kklors's Avatar

kklors

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

This lora is trained on 6-8K images of dirt, rust, scratches, dust, peeling paint etc. It will give objects a worn and aged look. For people or animals it works as a detailer (oftentimes).

Because the training data consists of high frequency details, going down with the Guidance to 1.8-2.2 will certainly help to retain them.

Strength 1.0 can sometimes produce 2d/abstract results with some seeds. Just change the seed or lower the strength to 0.8 or so.