Sign In

100% FLUX plus

58

624

26

Type

Workflows

Stats

624

0

Reviews

Published

Jan 22, 2025

Base Model

Flux.1 D

Training

Steps: 3,000
Epochs: 2

Usage Tips

Clip Skip: 2

Hash

AutoV2
E8144C50AE
default creator card background decoration
First Birthday Badge
vjleoliu's Avatar

vjleoliu

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.

About the workflow

realistic Skin / No plastic

The details of the picture can be enhanced. Images can be generated with text, or images can be reversed and regenerated through pictures, and then the details can be increased by enlargement.

Two Loras are loaded by default in the workflow. One is for turbo acceleration, and the other is the Lora I trained to improve the reality of realistic portraits. The link is here.

In the part of enlarging the picture in the workflow, new noise points will be automatically injected into the original picture for redrawing, thereby achieving a significant improvement in details, and it is also applicable to illustration styles. Here is an illustration Lora I just trained. You can load it and try. The effect is very good.