Sign In

Xe: Pixel LoRA

1.1k

Updated: Oct 6, 2024

stylepixel

Download

1 variant available

SafeTensor

146.28 MB

Verified:

Type
LoRA
Stats

247

49

134

Reviews
Published

Sep 18, 2024

Base Model

Flux.1 D

Training
Steps: 1,800
Epochs: 10
Usage Tips
Clip Skip: 2
Strength: 1
Hash
AutoV2
B2C3008FD5
Trigger Words
A pixelated image of a girl <...>
default creator card background decoration
Followers - 2867

2.9K

Likes - 33965

34K

Downloads - 334258

334.3K

Project Odyssey Contest Participant

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.

workspace_trainsamples_774485596919009605_88d074ec-70ed-4279-bc97-0b03c5e9e3f9.png

Create pixel-art works, similar to the lightweight pixel art style of independent games, not PlayBoy style.


Instructions

As a stylized model, it does not require activation words and can be used with any character lora.


Derived Checkpoint

Generally speaking, I will only train checkpoint with the same parameters and the same dataset if lora training is successful.

The advantage of checkpoint is that the character's memory ability is stronger.

The advantage of lora is that the training cost is much lower than the model, so it can be updated at a higher frequency.