Sign In

Luis Royo Flux (light version)

10

112

35

10

Verified:

SafeTensor

Type

LoRA

Stats

112

35

133

Reviews

Published

Feb 9, 2025

Base Model

Flux.1 D

Training

Steps: 9,600
Epochs: 12

Usage Tips

Clip Skip: 1
Strength: 1

Trigger Words

Lr0y0
Fantasy art by Lr0y0 of

Hash

AutoV2
312E40B7D1
Comfy Workflow Badge
tosave's Avatar

tosave

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.

New lightweight version for this legendary artist!

Trigger word : Lr0y0 or Fantasy art by Lr0y0 of

This Lora is an experiment in training targeted layers:

double 7 and 8 (seems to modify the style, the overall coloring)

double from 16 to 18 (more oriented on details?)

simple from 10 to 18 (refines the style of the image)

Result a small Lora and (maybe) more permissive on prompts.

So all this is totally subjective, following numerous tests of limiting blocks to the use of Lora.

Do not hesitate to give me feedback on your experiments!