Lcarterv1 - wonder woman V1

Name: Lcarterv1 - wonder woman V1
Rating: 5 (2 reviews)
Author: DMphotoart

126

Updated: Dec 21, 2023

character

superhero sexy female wonder woman woman

Download (36.11 MB)

Verified: a year ago

SafeTensor

Details

Type	LoRA
Stats	126 0
Reviews	Positive (13)
Published	Dec 21, 2023
Base Model	SD 1.5
Training	Steps: 1,956 Epochs: 16
Usage Tips	Clip Skip: 1 Strength: 1
Hash	AutoV2 28D2FD2D8B

1 File

default creator card background decoration

DMphotoart

Created on Civitai

This resource is intended to reproduce the likeness of a real person. Out of respect for this individual and in accordance with our Content Rules, only work-safe images and non-commercial use is permitted.

If you are this person or a legal representative of this person, and would like to request the removal of this resource, you can do so here.

Lcarterv1 - wonder woman V1

Hello friends,

I appreciate your time in reviewing my LoRa project and offering insights. Although this marks an improvement over my previous attempt, the results are still just satisfactory. I am reaching out for guidance and suggestions to enhance my model.

I've conducted training over 16 epochs, utilizing 10 portrait images of individuals of the same age but with different head poses, facial expressions, and hairstyles from approximately the same year. I have been cropping and scaling these images to achieve headshots of 512 by 512 pixels. However, I suspect that my settings might not be optimal.

I have adhered to standard settings, incorporating several full-body images alongside the headshots. Unfortunately, regardless of adjustments such as varying the dataset size, including or excluding body shots, the results remain consistently poor.

If anyone has the time or ideas to shed light on what might be going wrong, I would greatly appreciate your input. Feel free to share your thoughts or suggestions, and if possible, I can provide additional details or share test renders.

Thank you for your support!