DARK GEMINI Version 2.1

(The VAE included is from Waifu Diffusion 1.4 and is the one I’ve used for all my images. Awesome VAE)

Dark Gemini is a model designed for darker themes including dark fantasy, gothic fantasy and horror. You can render images from simple waifus to Kaiju, battles, abstract and surreal nu-gothic art. Whether you want to generate a man, a woman, an animal, a creature, a monster, a Kaiju or a landscape/cityscape and you’re into the darker things. Then give this a try and let me know what you think!

Created by merging together selected models after thorough individual testing, into 6 different merged what I refer to as sampler models.

These are then merged with my baseline model using merge block weighted extension.

Merge block settings (12 in, 1 mid, 12 out block lanes) using what little knowledge is available.

Along with my own experimentation to merge the data I want and scrap what I don’t want to get the model as close

to where I want it to be as possible with the current knowledge

The following models were used in some capacity to create this merge:

• UnstableSamInkDream

• Open Journey v1

• F222 v1

• Elysium Anime v2

• Elysium Anime v3

• Elldreth Vivid Mix

• Elden Ring

• Eimis Anime Diffusion v1

• hAs3DKX11_3dkx11

• Healys Anime Blend

• Hero Calm

• Shirayuki Anime

• RPG V2 Beta

• Seek Art

• Kenshi

• Nerfgun3 NewArtModel3

After restarting the process several times to attempt new configurations of the sampler models, I finally arrived at where the model can no longer be improved for my intentions.

———————————————————————————-

A Small Intro

GEMINI V2.1 Model generates art styles from anime to more western style splash art or If you want to render 2.5d (3d rendered in 2d, one way to accomplish this is to write: “line art, sketch art” in negative prompt.) After discovering the CLIP was off, I reset it and released Gemini 2.1 while keeping 2.0 as well for its different style.

I’ll explain a few things on how this model responds to prompts:

If your prompt contains a lot of different details that your character is doing.

Try to first condense it, make it more simple but precise. If your prompt still ends up being very long.

Then make sure the prompt loops at least once, this will make the AI take another pass to read through it.

I don’t know if repeating the input for the prompt you want the most has any impact,

but if it does then I don’t see there being any other way than going beyond 75 tokens and letting it do a second pass.

Example style prompts:

• Nu-Gothic Art Style

• Victorian-Gothic Art Style

• Splash Art Style

• Anime Art Style

• Dark Anime Art Style

• Dark Fantasy Art Style

• Norse Art Style

Art Style can be switched out with Artwork, which can alter the results a tiny bit giving you the same aesthetic but different renders. Art can also be removed from the prompt to create “X Style Infusion” or “X Style Aesthetic”.

———————————————————————————-

THIS SECTION ONLY APPLIES TO 2.1

In 2.1 after the clip has been reset, many prompts dislike when you place style or design tags at the start of the prompt. It should instead be moved to the final stretch when all art, style, color, design, composition, light, camera etc is written. Since we’ll be using weights, the effect of the location of the prompt has less impact than in 2.0.

If you want to render 2.5d (3d rendered in 2d, one way to accomplish this is to write: “line art, sketch art” in negative prompt.)

For example:

To get two characters to fight and actually make contact, actually stab or slash. It helps to add tags such as: full contact, close quarter, stabbed, loses limb, blood gushing, wounded.

These can be placed sparsely around the entire prompt and experiment with their weights until you get something you want. Of course it also matters how else you write the prompt so I will give you an example and you can trial and error from there!

• ((extremely detailed:1.22) two lethal swordsmen dueling to the death in the phantom ruins:1.22), (loses limb:1.08), (blood gushing:1.1), (Facing each other:1.06), (Full Contact:1.04), (Stabbed:1.04), (One has short blonde hair and one has long dark red hair:1.20), (each of the two is wearing unique enchanted (ultra detailed:1.22) legendary armor:1.22), (wounded:1.14), high intensity, (swords daggers and magic:1.17), (magic circles:1.10), (2021 anime art style:1.25), (digital illustration:1.20), (digital art:1.20), (splash art style aesthetic:1.15), (dramatic angle:1.15), (masterpiece:1.25), (best quality:1.25), (highres:1.25), 8k, (intricately detailed:1.22), (exquisite line art:1.16)

This is accompanied by a negative prompt modified from the general one I use (which still applies to 2.1)

• low quality, no quality, bad quality, low resolution, lowres, normal resolution, no detail, low detail, deformation, text, title, Description, logo, watermark, jpg artifacts, jpeg artifacts, disfigured, deformed, bad anatomy, , extra leg, extra arm, extra finger, no head, no body, half body, melted face, cropped, cropped head, cropped body, missing finger, 6 fingers, 7 fingers, 4 fingers, 3 fingers, extra thumbs, no thumb, noodle fingers, contorted fingers, spaghetti fingers, wavy fingers, extra long fingers, spaghetti body, contorted, contortion, siamese twins, conjoined twins, conjoined body parts, unnatural pose, hand on blade, faulty grip, bad grip, dropping sword, no sword, mishandling sword, handle with no blade, missing blade, missing sword, swords in the air, sword artifacts, floating weapons, healthy, big breast, massive breast, major breast, big tits, massive tits, major tits, hentai, eroge, nukige, pornographic, porn, XXX, erotica, loli, lolicon, skimpy, slutty, nude, nudity, naked

As you can see I also removed NSFW from negative prompt because it can interfere with combat as blood and violence could be considered NSFW. Down below is some more information if you want to replicate the image I rendered.

Steps: 30, Sampler: DPM++ 2S a, CFG scale: 7, Seed: 2930654821, Size: 1024×640, Model hash: 49fc1bfcac, Model: Dark_Gemini_v2.1, Clip skip: 2

———————————————————————————-

THIS SECTION ONLY APPLIES TO 2.0

Placing one or two style reference tags at the start of the prompt will focus more on achieving that look than it will on your active prompt of your choice. This however happens a lot less when the tags are much simpler.

For example

Nu-Gothic Art Style Vs Portrait Of

Nu-Gothic Art Style or Nu-Gothic Artwork and similar prompts will have a much greater impact on the overall prompt when placed first.

Rather than in the final composition phase of the prompt. When using Portrait Of, it still won’t know what style.

So don’t forget to let it know during the final phase of the prompt, or you might get some strange and very poor results.

Here’s three examples of the prompt layout I used when creating the example images. Replace XCONTENTX with your typical prompt content be it a character, an item, a landscape etc. Then XCOMPOSITIONX are style, design and command prompts that affect how the prompt will look like, beyond what’s already written (these three weren’t the only ones I used, but should serve as examples to get you started!)

• “(X art style1.30), (X style infusion:1.20), (digital illustration:1.25), XCONTENTX, (digital art:1.20), (X artwork:1.20), XCOMPOSITIONX, (masterpiece:1.35), (best quality:1.35), (highres:1.35), 8k”

• “(X artwork:1.30), (X Aesthetic:1.20), (Concept Art:1.20), XCONTENTX, (digital art:1.20), XCOMPOSITIONX, (masterpiece:1.35), (best quality:1.35), (highres:1.35), (8k ornate octane render live 2.5d:1.31)”

• “((Portrait of:1.38) (Character Description:1.39):1.45), XCONTENTX, (X Style Infusion:1.35), (X Artwork:1.40), (Extremely Fine Line Art:1.20), (Intricately Detailed:1.30), XCOMPOSITIONX, (masterpiece:1.35), (best quality:1.35), (highres:1.35), 8k”

• You can also look on some of the images that come with prompt information and use it for testing or as a guide. Eta Noise Delta is always 0, 1 or 31337. I always use kl-f8-anime2 for my VAE.

———————————————————————————-

THIS APPLIES TO EITHER VERSION:

There are other purely experimental tags that can affect your prompt:

• Clockpunk

• Gearpunk

• Diesel Punk

• Cyberpunk

• Darkcore

• Futurecore

• Ethercore

Keep in mind that the model is mostly tested on Gothic and Dark Fantasy themes in a range from anime to western style art or the hybridization within. It’s also been tried and evaluated by a handful of beta testers that are themselves model makers and given the thumbs up to exit beta stage. They tested it for waifus, husbandos, chibis, animals, famous characters (it failed a lot on that, so might need an embedding) as well as it’s intended use. Myself and the testers also tried cyberpunk, futurepunk, dieselpunk, steampunk etc with some promising results but as that isn’t the primary focus of this model I can make no guarantees to your success. However I’d love to see your successes!

It’s been tested using the kl-8-anime2 VAE and Skip Clip 2 with delta noise of 0 or 31337, ETA Noise for Ancestral and DDIM is 0.67 on 2.0 and 1 on 2.1

The negative prompt that has served as a foundation for most of my prompts in 2.0 and 2.1 is the following:

• low quality, no quality, bad quality, low resolution, lowres, normal resolution, no detail, low detail, deformation, text, title, Description, logo, watermark, jpg artifacts, jpeg artifacts,
  disfigured, deformed, bad anatomy, extra leg, extra arm, extra finger, no head, no body, half body, melted face, cropped, cropped head, cropped body, missing finger, 6 fingers, 7 fingers, 4 fingers, 3 fingers, extra thumbs, no thumb, noodle fingers, contorted fingers, spaghetti fingers, wavy fingers, extra long fingers,
  spaghetti body, contorted, contortion, siamese twins, conjoined twins, conjoined body parts, unnatural pose,
  big breast, massive breast, major breast, big tits, massive tits, major tits, hentai, eroge, nukige, pornographic, porn, XXX, erotica, loli, lolicon, skimpy, slutty, NSFW, nude, nudity, naked

———————————————————————————-

The model uses the CreativeML Openrail licensing and I permit the use of my model in merges and whatever you generate is yours to do with as you please so long as you follow your local laws.

The sale of the model is NOT permitted, this model is free and will remain free for anyone that wishes to use it. If you want to redistribute the model somewhere I haven’t uploaded it, I would prefer you contact me and ask me to upload it there. However I make an exception for very language specific sites (non-English and non-Swedish) as long as you properly credit me and link back to one of the primary sources.

If you have any questions or need advice, please don’t hesitate to ask. Due to private issues, there may be a delay but I will try to help as many as possible and if there are questions that are very similar and repeated. I will probably just make a FAQ of some sort.

You can find the channel for Dark Gemini v2 on the Stable Diffusion discord server under models-embedding or by clicking this link https://discord.com/channels/1002292111942635562/1070414828067377323

It would be nice to get some activity in there and see what interest people have in my model and continuing to use it. What types of models or Lora people need

Have fun and happy prompting!

//Cryonicus