Sign In

Luna_Flex_v3_flux

70

Updated: Aug 19, 2026

character

Download

1 variant available

SafeTensor

18.38 MB

Verified:

Type
LoRA
Stats

79

42

173

Reviews
Published

Mar 7, 2025

Base Model

Flux.1 D

Training
Steps: 6,000
Epochs: 6
Usage Tips
Clip Skip: 1
Hash
AutoV2
DF7392038A
default creator card background decoration
Reactions - 25870

25.9K

Followers - 1563

1.6K

Likes - 74

74

Created on Civitai

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 is another update to my Luna model and I will continue to update it. Please let me know if you have any suggestions on how to make it better.

============================ Flux ==========================

Engine = kohya

Epochs = 6

Num Repeats = 4

Train Batch Size = 4

Steps = 1250

Resolution = 512

Clip Skip = 1

Unet LR = 0.00050

Text Encoder LR = 0.00000

LR Scheduler = cosine_with_restarts

LR Scheduler Cycles = 3

Min SNR Gamma = 5

Network Dim = 2

Network Alpha = 16

Noise Offset = 0.10

Optimizer = AdamW8Bit

Optimizer Args = weight_decay=0.01, eps=0.00000001, betas=(0.9, 0.999)