Tensor.Art
Create

The Araminta Experiment

CHECKPOINT
Reprint

Updated:

Fv5
Fv4
Fv3
Gv2
Fv2
Ev3
Fv1

Now

Comparison gallery here: Ev4 - Ev3 and Fv1 - Ev4

Current SOTA model in my experiment:

Base model: Fv1 or Ev4 (if you accept unexpected NSFW) or Cv6... Fv1/Ev4 are biased toward NSFW, but still better in many aspects.

NSFW model: Fv1

Illustration : Fv1 (NSFW) or Cv6 (SFW)

Starting from E serie, models are evolving sometimes by merging with other models (thanks to other contributors!), but mostly via training on my own dataset: a modest dataset (~2000 images currently), but I try to somehow compensate with quality and originality.

Starting with Fv1, I have included many synthetic images I created using previous versions: playing hard with prompt and retouching when necessary the result in Photoshop in order to have a dataset which contains many original images.

Version Detail

SDXL 1.0
About this version Improved realism compared to Fv3 for any kind of image (NSFW or SFW): I would say that Fv4 begins to produce some really realistic images finally :) But as realism is improved, styled non-realistic images (illustration for example) are really not the strength of this model: Gv2 is even more the way to go for these kind of images. Based on Fv3 merged with biglustydonutmixNSFW_v12 and xxxRay_v10 as well as some personal Loras.

Project Permissions

Model reprinted from : https://civitai.com/models/463163?modelVersionId=716653

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts

Describe the image you want to generate, then press Enter to send.