Gwendolyn Tennyson (Lucky Girl) - Ben 10版本v2.0 (ID: 103519)

LoRA for Gwendolyn Tennyson from Ben 10.

If you like my work and want to support me, please consider supporting me on my Ko-fi page. I'm open to donations and commissions for art and LoRAs with no censorship.

*Refer to version notes for Version 2 of this LoRA and how to use that one

I trained it with 74 pics, which was a mix of mainly fan art and some screencaps. I trained it at 10 epochs with a dim/alpha of 16/8.

Leans to a semi-real look mostly, but somewhat more cartoonish at higher LoRA weights. Let me know how it goes for you. Read stuff below on guidelines and known issues :)

Triggers:

Input "Gwendolyn Tennyson, 1girl" after the LoRA near the start of the prompt.
Input "orange hair, green eyes" for more consistency if needed, but I didn't find it necessary.
Input "long sleeves, white pants" for classic clothes. NB: can place in negative prompts if the clothes are stubbornly appearing.

Notes:

My experience has shown scale 0.7 ~ 1 works best; my best results were 0.7 for semi-realistic, but overall favourite was 1.
My prompt order shown in the sample pictures worked best for me.
Works on different models though weights may need to change for good results.
I used Anything4.5 model and Midnight Maple model. Midnight Maple gave best results for this LoRA for me.
Refer to my pictures for examples and what upscaler I used, keep in mind I have used other textual inversions to help with poses and negatives.
I think this is personally very flexible, at least in terms of changing poses, clothes etc. Other LoRA's and/or Models seem to bring out the more cartoon appearance so experiment for styles.

I don't think people read entire descriptions like this, but congrats if you do

描述:

Lora Update for Gwendolyn Tennyson Alternate Outfits (Ben 10)

If you like my work and want to support me, please consider visiting me on my Ko-fi page. I'm open to donations and commissions for art and LoRAs with no censorship.

This is not meant to replace the previous LoRA. It's merely so that you can get alternative outfits, namely the "Lucky Girl" one. Though, it can still easily produce Gwen pictures with her in different outfits, it won't be able to make pictures of her in her classic blue shirt.

I trained this LoRA with the same dataset as the previous version except I replaced most of the images with Gwen in her classic outfit with ones of her in her "Lucky Girl" outfit. In addition I included a few pictures of her in her green swimsuit, but this focuses on her Lucky Girl look.

Please play around with the LoRA weights. Let me know how it goes for you. Read stuff below on guidelines and known issues :)

Triggers:

The global activation tag is "Gwendolyn_Tennyson, 1girl" which is the same as before. Though it will now skew towards giving her the new outfit instead.

To get her Lucky Girl outfit you may want to add the prompts below:

mask, necklace, gloves, bodysuit

NB: can place individual items of clothing in the prompts and/or in negative prompts if the clothes are stubbornly not appearing and you don't want them. For example if you put the triggers above and put mask in negatives, you will get her in her Lucky Girl outfit without the mask.

Notes:

My experience has shown scale 0.7 ~ 1 works best; my best results were 1.
My prompt order shown in the sample pictures worked best for me.
Works on different models though weights may need to change for good results.
Refer to my pictures for examples and what model and upscaler I used, keep in mind I have used other textual inversions to help with poses and negatives.

You likely won't get a perfect example image of her Lucky Girl outfit, but it should be relatively similar. I noticed that using different models with this drastically changes how different the suit looks so experiment.