Sign In

Star Wars sith outfit (flux,pony and 1.5)

722
7.6k
5.6k
135
Verified:
SafeTensor
Type
LoRA
Stats
546
263
Reviews
Published
Sep 20, 2024
Base Model
Flux.1 D
Trigger Words
sithoutfit
sithoutfit robes
Hash
AutoV2
A71EA0F147
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.

UPDATE

-Added Flux version

-Flux is very good at generating sith outfits out of the box, but this lora gives a little diffrent aesthetic, especially with sith face paints. Other then that it generates less cloaks, more robes and different belts. I will try to prepare some comparison images to highlight the differences.

-When prompting for a more unusual scenario use "sithoutfit robes" prompt to reinforce the lora, in this cases the difference between version with lora and without will be more visible.

UPDATE:

-Added Pony Version

-Pony does not produce satisfactory (to me) sith outfits out of the box, so here we go. For realistic pony checkpoints you will get similiar (altough distinct) outfits for both we LORA and without. For anime/cartoon checkpoints the difference is much more visible. I will post a simple comparison.

-Basic trigger is "sith outfit", but if you are trying to pair it with abnother LORA its good to add "black robe,sith robe".

-Add "face paint","alien","pale" to the neg to supress unwanted features.

UPDATE V3:

-All around better quality

-Outfit varies a little more

Trigger phrase is sthoutfit.

This version works best at 0.7 or 0.8 strength

if you want to supress lightsabres completely its good to put them in the negatvice rpompt with big weight.

You will see that there is no Anakins outfit in this LORA. I tired to use it in one of the first versions, but this is what i got:

For me those are jedi, not sith, that is why i got rid of this outfit in the data set.