Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
* This model is not available for use and might generate different characters compared to the ones seen in the images.

Model Description by Creator

Hi again and welcome to SeekGold.

SeekGold is part of the "Seek" series (you probably already saw my SeekWest) where I focus more doing a world-embedding instead of a characters or landscapes only. SeekGold will create gold, metal gold, abstract dripping landscapes, characters, etc.

This is also my first public Lycoris (LoCon in this case).

For curious people, I have been messing for couple months training LoCons and LoHa's privately and now it's time to upload (and retraining) them since I polished my training, dataset, etc. (meanwhile I get ready for SDXL).

Token is LQDGOD

How does this works?
*************************

  • FIRST OF ALL: Make sure you have everything ready to use LyCoris on your WebUI. Install this extension on your WebUI (Recommended if you have an older repo).

  • I also recommendto use this negative embedding:
    https://civitai.com/models/7808/easynegative

  • Or this combination words:
    "glass, pedestal, socle, basement, camera, subsurface, underwater, hypermaximalist, diamond, (flowers), water, (leaves) (worst quality:2), (low quality:2), (normal quality:2), border, frame, poorly drawn, childish,((dof)),bad hands, ugly hands, unnatural hands"

    Back to the embedding:

- It works on every model I have tested and at some high degree of flexibility. I'd recommend RevAnimated but you can go Colorful, Faetastic, Dreamshaper, AnyLora, etc. I'd recommend Clip Skip 2 but with 1 also works (I think a bit worse).

- You can go from 0.6-1 (with the new LyCoris extension).

- You can go from 0.9-1.3 (With the old one, the one I used to create the outputs)
(read the comments for this, please).

- Prompt like normal but add "in the style of LQDGOD", "LQDGOD concept", etc.

- There are subtokens like dripping and gold which drags more to the style but most of the time you won't need them since token is very very powerful.

- If you feel that the style is killing the concept (which is probable in the new LyCoris extension) consider to go under 0.9 till 0.6.

- You can prompt with the LoCon without the token using subtokens and words dragging to the style.

This model is good for
************************

- Characters wearing gold objects, armors, suits. and statuesque alike.
- Characters mixed with gold element and "symbio"
- Abstract gold landscapes and gold type structures or vehicles.
- Dripping materials


This model is NOT designed for:
**************************************

- It wasn't test on Realistic models so I can't say it will work as in the others.

IMPORTANT!

I wrote an article here and it's like my finetunning diary for the ones interested with releases upcoming, trainings done, exclusive patreon models previews, personal thoughts, etc. So if you want to see what I'm planning or what I'm into, feel free to take a look.

Thanks as always for all the support and please keep supporting me and my pal so we can create more quality content in our Patreon for you all.


Feel free to throw feedbacks, reviews (thanks guys!), critics and so on. I always read them and make all on my hand to make quality things.

David.

Images Generated With This Model

<lora:Lqg:1> superman, portrait, LQDGOD style, sitting
N/A
Hidden For Public Users
<lora:Lqg:1> superman, portrait, LQDGOD style, sitting
<lora:Lqg:1> a man standing in front of dripping LQDGOD storm sea
N/A
Hidden For Public Users
<lora:Lqg:1> a man standing in front of dripping LQDGOD storm sea
<lora:Lqg:1> dog inside a glass made of LQDGOD
N/A
Hidden For Public Users
<lora:Lqg:1> dog inside a glass made of LQDGOD
<lora:Lqg:0.7> cat animal astronaut side portrait in LQDGOD style
N/A
Hidden For Public Users
<lora:Lqg:0.7> cat animal astronaut side portrait in LQDGOD style
<lora:Lqg:0.8> a cat in the style of LQDGOD
N/A
Hidden For Public Users
<lora:Lqg:0.8> a cat in the style of LQDGOD
<lora:Lqg:1> side view portrait a man standing in front of dripping LQDGOD storm sea
N/A
Hidden For Public Users
<lora:Lqg:1> side view portrait a man standing in front of dripping LQDGOD storm sea
<lyco:Lqg:0.8> a man in front of dripping LQDGOD storm sea
N/A
Hidden For Public Users
<lyco:Lqg:0.8> a man in front of dripping LQDGOD storm sea
<lora:Lqg:0.8> a wizard male portrait in the style of LQDGOD, summoning energy
N/A
Hidden For Public Users
<lora:Lqg:0.8> a wizard male portrait in the style of LQDGOD, summoning energy
<lora:Lqg:1> house inside a glass made of LQDGOD
N/A
Hidden For Public Users
<lora:Lqg:1> house inside a glass made of LQDGOD
<lora:Lqg:0.7>  submarine in the LQDGOD style
N/A
Hidden For Public Users
<lora:Lqg:0.7> submarine in the LQDGOD style

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.
Train Your Own Model

Your All-in-One AI Image Solution

AIEasyImage brings AI image technology to everyone. Create stunning visuals, edit like a pro, and develop your unique style – all with the power of AI. No technical skills required!