Ava2000's picture
Update README.md
7882892 verified
|
Raw
History Blame Contribute Delete
1.98 kB
metadata
tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - output:
      url: images/0d15a5f3-8bc0-43ac-af9e-53c0c804f785.png
    text: 'masterpiece, best quality, traditional media, sketch, jaggy lines, '
    parameters:
      negative_prompt: >-
        text, long body, lowres, cropped, lowres, jpeg artifacts, (signature,
        artist name, watermark, username, english text, signature:1.4), simple
        background, conjoined, out of frame, out of frame, censored, bar censor,
base_model: calcuis/illustrious
instance_prompt: akabl3akstyle

Akableak Style - Illustrious

Prompt
masterpiece, best quality, traditional media, sketch, jaggy lines,
Negative Prompt
text, long body, lowres, cropped, lowres, jpeg artifacts, (signature, artist name, watermark, username, english text, signature:1.4), simple background, conjoined, out of frame, out of frame, censored, bar censor,

Model description

The style of Akableak.

I made this lora to try and reproduce the style of Akableak.

Illustrious v3

Learned some new tricks and redid the lora, with the same dataset from v2. This is the definitive version!

Illustrious v2

The new improved version, with a better strength and style adherence. It is also made with a new dataset, because I lost the original set. So prompts may differ from before. The prompting is the same as version 1 below.

Illustrious v1

For all versions I recommend you use: masterpiece, best quality, amazing quality, very aesthetic, high resolution, in your prompt and I myself am using the following negative prompt: text, abstract, glitch, deformed, mutated, ugly, disfigured, long body, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, lowres, (worst quality, bad quality:1.2), bad anatomy, jpeg artifacts, signature, watermark, username, signature, simple background, conjoined,

This LoRa is trained on Illustrious 0.1, but I made the above showcase images in different checkpoints, because their style was more to my liking.

Trigger: akabl3akstyle,

Advised strength: 0.6-1.0

Trigger words

You should use akabl3akstyle to trigger the image generation.

Download model

Download them in the Files & versions tab.