Dark Gemini 2.1 out, but both 2.1 and 2.0 are worth keeping as they have different aesthetics around the same theme. I'll post a short guide for how 2.1 differs from 2.0, as the prompts are quite different. Not today though, but I still try to have it done soon. Meanwhile there is a guide over at https://civitai.com/models/6209/dark-gemini-v21
DARK GEMINI Version 2
IMPORTANT NOTE: If you downloaded the pruned version before Feb 3rd 13:37 (accident I swear) then you're sitting on one with different clip stats than the full variant through which I've tested this model. I've fixed it and reuploaded, I will be looking at the reset version to see if it holds up and if it does. I will release it as the other part of Gemini, perhaps Darker.
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.
GEMINI V2 Model generates art styles from anime to more western style splash art or 2.5d (3d rendered in 2d, best accomplished by putting “line art, sketch art” in negative prompt.) 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. 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.
Style or Design Prompts are there to provide the aesthetic and genre or looks of your image, there are many ways to combine. Or to manipulate them to generate really cool images.
- 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”.
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"
Tested:
- Darkcore
- Devilcore
- Deathcore
- Gothcore
Experimental:
- Clockpunk
- Gearpunk
- DieselPunk
- Cyberpunk
- Futurepunk
- Etherpunk
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 been tested using the kl-8-anime2 VAE and Skip Clip 2 with Eta noise seed delta of 0 or 31337.
It's also been tried and evaluated by a handful of beta testers that are themselves model makers
They gave it 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!
The negative prompt that has served as a foundation for most of my prompt 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. I make an exception for language specific sites (non-English/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.
Have fun and happy prompting!
//Cryonicus