Like the model ❤️
CHECK NEW VERSION DETAILS!
BUZZ HELPS TO TRAIN MORE MODELS
Welcome to my first LoRA by FluxDev!
Here's the difference between using the LoRA and not using it... Does it convince you?
Honestly, I've been looking for LoRAs with vintage/aesthetic poses for Pinterest or Tumblr... Since I couldn't find one, I decided to create it myself. I hope you like it...
I trained it with only 2500 steps, and so far, the testing results are promising.
Description
In this version, I have added images with dramatic_lightning. Use this trigger word if you want to add dramatic lighting to your images: dramatic_lightning.
Additionally, I have added some Western and male models to improve versatility.
As a recommendation: do not try to over-detail the poses, as this can conflict with the model and cause mutations.
Trigger words: aesthetic_pose, dynamic_pose, dramatic_lightning.
I have trained the model with some anime images, so it also works with anime.
FAQ
Comments (5)
Love having more poses but needs more varied data set. turned a black man in my picture into an asian guy with mascara eyelashes
yeah, im sorry to hear that.... but yes, the dataset is based in asian womans. In the last version i used more occidental humans, but yeah is like a 25% vs 75%
You have the version 3.0, is trained with more variety, so it should fix your problem :)
😭😂😂😂😂😂
ahaha i had the same, in the murky, intruegue light room is a silloughette of man with burning eye look of an asian guy with eye lush. I bet it was a picture of a nightmare for getero guy.
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.


















