Details
Related
Asari Diffusion V2
Asari Diffusion V1
Asari Diffusion

Asari Diffusion

1.1K
107
690
#Anime
#Female
#concept
#alien
#race
#woman
#Realism
#video game
#women
#mass effect
#Anime
#GIRL
#????
#Female
#alien
#race
#woman
#Realism
#video game
#women
#mass effect

This is a lora meant to create a variety of asari characters. This is a model trained with text encoder on about 30/70 SFW/???? art, primarily of realistic nature. The lora is not particularly ?????, surprisingly, but do consider the origins when tagging.

Separate anime release is available as well. https://civitai.com/models/20081/asari-diffusion-anime

Tags: "Asari" is the main trigger. This lora is trained to reproduce blue, green and purple skin with quite a few possible variations of color (but see issues, below). Other tags as appropriate for your model, nothing special. Since the model is trained on a variety of ???? ????????? pictures work with obvious tags. Have not tried anything hardcore, but should work with an appropriate base model.

Tagging clothes description seems to be enough to avoid ??????.

The model has not been trained to recognize any particual Mass Effect characters, but you will sometimes see Liara's face.

Issues: Sadly, skin color tags often bleed into other parts of the shot, I was not able to figure out many ways around it other than to tag carefully or not tag the skin at all and rely on random. It happens less with blue_skin.

View Translation

Rating & Review

4.8 /5
0 Ratings

Not enough ratings or reviews received yet

no-data
No data available
F
Chat with the model
Notice
2024-06-08
Publish Model
2023-03-20
Update Model Info
Model Details
Type
LORA
Publish Time
2023-03-20
Base Model
SD 1.5
Trigger Words
asari
blue_skin
purple_skin
green_skin
Copy
Version Introduction

A significant improvement over the last version, most likely the last release.

  1. More consistent faces at a distance

  2. Less human skin issues

  3. Less artifacts and mutations, more successful generations

  4. Does not force realistic style as much

  5. Usable across wider range of checkpoints, just experiment with lora weights

While it works much better with anime models now, I still recommend using the dedicated anime releases for Anything V4 and AOM, as the loras there are more responsive, but this is a good general model.

Style and Models: Works well with the most checkpoints, recommended weights for the ones I tried. All examples are straight txt2img

DeliberateV2 (0.6-0.9)

Realistic Vision (0.6-0.9)

RPG (0.7 - 1)

Dreamshaper (0.5-0.8)

Chilloutmix (0.8-1)

DalcefoeV4 (0.7-0.9)

Dalcefoe oil paint V3 (0.7-0.9)

DalcefoePaintingV4 (0.7-0.9)

AOM (0.8-1.0)

Anything V4 (1.0-1.2)

Anything V3 (1.0-1.2)

ExpmixLinev20 (0.9 - 1.0)

Settings: Works best at low to mid CFG (3-6), I personally prefer to pick lower end of the scale.

License Scope
Model Source: civitai

1. The rights to reposted models belong to original creators.

2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim

Creative License Scope
Online Image Generation
Merge
Allow Downloads
Commercial License Scope
Sale or Commercial Use of Generated Images
Resale of Models or Their Sale After Merging
QR Code
Download SeaArt App
Continue your AI creation journey on mobile devices