---
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
widget:
- text: '-'
  output:
    url: images/image 2.png
- text: '-'
  output:
    url: images/image 1.png
- text: '-'
  output:
    url: images/image.png
- text: '-'
  output:
    url: images/image g2.png
- text: '-'
  output:
    url: images/image b.png
- text: '-'
  output:
    url: images/image l.png
- text: '-'
  output:
    url: images/image a.png
- text: '-'
  output:
    url: images/image vv.png
- text: '-'
  output:
    url: images/image d.png
- text: '-'
  output:
    url: images/image c.png
- text: '-'
  output:
    url: images/image t.png
- text: '-'
  output:
    url: images/image w.png
- text: '-'
  output:
    url: images/image g.png
- text: '-'
  output:
    url: images/image r.png
- text: '-'
  output:
    url: images/image x.png
- text: '-'
  output:
    url: images/image n.png
- text: '-'
  output:
    url: images/image 6.png
- text: '-'
  output:
    url: images/image 4.png
- text: '-'
  output:
    url: images/image 3.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: >-
  Star Trek TNG, TV still, Picard, Riker, Troi, Crusher, Data, Worf, Romulan,
  Klingon, Borg, on the Enterprise, control panel, Borg, Klingon, Romulan,
  wearing a red Starfleet uniform, wearing Klingon armor, wearing a Romulan
  uniform

---
# Star Trek SDXL

<Gallery />

## Model description 

I was inspired upon using Dall-E3, seeing how well it recreated the look of the classic show Star Trek The Next Generation, but being disappointed that it could only recreate Picard.

This lora includes changes to the text encoder, and the training data was captioned by hand by me, so you&#39;ll be able to invoke different characters by name, different sections, different clothing, etc. I hope to demonstrate this in images, but here are some of the key terms:

Main keywords: Star Trek TNG, TV still

Characters:
Picard
Riker
Data
Geordi
Worf
Crusher (Beverly, I left out Wil)
Troi
Romulan
Klingon
Borg
(there are some more, leaving them a secret for fun (to whom?))

Clothing:
wearing a (red&#x2F;yellow&#x2F;blue) Starfleet uniform (other colors can be invoked if you try to varying degrees of success)
wearing Klingon armor
wearing a Romulan uniform
(and some more)

Objects:
Geordi wears a &#39;visor&#39;, Worf has a &#39;metal sash&#39;, Borgs may have a &#39;holographic eyepiece&#39;. I tried to train the lora on many different things.

Environments:
&#39;On the Enterprise&#39; - generically included for on the ship
&#39;In a Klingon building&#39;
&#39;In crew quarters&#39;, &#39;In engineering&#39;, &#39;on the bridge&#39;, &#39;sitting in the captain&#39;s chair&#39; etc can be invoked to a degree
I included terms like &#39;atmospheric&#39;, lighting colors, &#39;dark&#39;, viewing angles, etc.

I called all the interfaces on the ship &#39;control panels&#39;, the screen on the ship is the &#39;ship&#39;s viewscreen&#39;, you can try to invoke different ship exteriors (to little success)


Training:
Bog-standard lora with constant rate 1*10^-5, &gt;1500 images (hand picked), ~8000 steps

## Trigger words

You should use `Star Trek TNG` to trigger the image generation.

You should use `TV still` to trigger the image generation.

You should use `Picard` to trigger the image generation.

You should use `Riker` to trigger the image generation.

You should use `Troi` to trigger the image generation.

You should use `Crusher` to trigger the image generation.

You should use `Data` to trigger the image generation.

You should use `Worf` to trigger the image generation.

You should use `Romulan` to trigger the image generation.

You should use `Klingon` to trigger the image generation.

You should use `Borg` to trigger the image generation.

You should use `on the Enterprise` to trigger the image generation.

You should use `control panel` to trigger the image generation.

You should use `Borg` to trigger the image generation.

You should use `Klingon` to trigger the image generation.

You should use `Romulan` to trigger the image generation.

You should use `wearing a red Starfleet uniform` to trigger the image generation.

You should use `wearing Klingon armor` to trigger the image generation.

You should use `wearing a Romulan uniform` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/Jigen/Star_Trek_SDXL/tree/main) them in the Files & versions tab.