If you'd like to support me and do more:
https://ko-fi.com/edgonkofi - commissions open! I can make a model for you!

Royal Gowns

We do like to dress to impress, don't we? What's more, we are lacking in beautifully detailed clothing.

Fear not friends. I've got your back.

More beautiful clothing is incoming, beautiful royal gowns to please your eyes and dress your women with style!

Special shout out to @Zovya, I am very impressed with the results of the clothing on her model as I am showcasing it here.

I highly recommend you download either her model A-Zovya RPG Artist Tools - V2

or my Amixx - v1.0-pruned-fp16

when prompting with these models.

Have fun!

Download this LoCon and get some gowns!

Trained on AOM3. This is a LoCON, so please install the appropriate extension to be able to use it.

Consider tipping me through Ko-Fi!

https://ko-fi.com/muscleenjoyer

キャラクタータグは"liko_\(pokemon\)"とかでうまく再現できる

服装は別で指定する

強さは0.6~0.8くらいがいい感じ

背景に影響が出てるからネガティブプロンプトとかでうまく調整したほうがいいかも

Character tags can be successfully reproduced with "liko_\(pokemon\)" and so on.

Clothing is specified separately.

Strength should be around 0.6~0.8

The background is affected, so you might want to adjust the negative prompts or something.

This locon:

• Adds contrast

• Makes colors more vibrant

• Adds details, including background details

• Improves costumes

• Works fine with landscapes or portraits

• Doesn't mess with your overall style, whether it's cartoon, photorealistic, or whatever

• Plays well with other locons, loras, etc.

Looks good when weighted at 1.0, and can be really dramatic at 1.5 to 2. The trigger words are helpful but not necessary.

This as created using the amazing conceptmod by @ntc, running for 600 iterations with a prompt of "#:0.1|~beautiful, elegant, confident". I exported the locon a number of different ways, and this one seems to be a reasonable size while preserving fine detail. See the conceptmod tutorial for details.

If you create any good images using this LoRA, please consider sharing them by leaving a review. Thank you!

Fit girl LyCORIS update

In the process of making Muscle Girls 2.0, I sorted out some girls with fewer muscles and made them into a LyCORIS

• This version is a LyCORIS, please refer to the relevant instructions of LyCORIS

• This version is mainly for leaner women, they don't have thick thighs and bodies.

Three body types:

• without trigger word: Modify body shape, with less muscle

• Fit: Some muscles, less visible abs, Ab_lines and Navel can enhance the body shape.

• Ripped: More muscles, usually with visible abs, can be used with Abs and Navel

1.0

This LoRA can help generate muscular females, improve muscle tone and thighs, plus tight-fitting clothing with muscles.

• Common muscle-related prompts may work, including abs, leg muscles, arm muscles, and back muscles.

• Without the need for trigger words, this LoRA can also fix body shape.

• Not good at generating hyper muscles.

• Add Prompt "navel" makes abs look better IMO.
  

Note: if there are unexpected bikini strings around hips, add "shimakaze \(kancolle\)" or"high leg" to the negative prompts may help get rid of them, sometimes.

Kerrigan Starcraft 2 Cosplay Lycoris (TEST Version)

I'm experimenting with LoCon parameters for attire and concept, depending on your model / prompt might hit or miss a lot. Note: limited pose variation from her dataset, you may need to use control net

Works best with FantasticMix model. ( v2.0 is better imo )

fantasticmix_real - v3.0 | Stable Diffusion Checkpoint | Civitai

Trigger words : srkg, long hair, claws, alien, monster girl, wings,

Recommended Weight : 0.6-0.8

For best result use Dynamic CFG Threshold:

• Mimic = 10 | Clamp Percentile 99.5

• Min. Mimic Scale = 0, Cosine Up

• CFG Scale Sch. = 15, Half Cosine Down

If subject face is small / far away use: DDetailer Script with bbox anime face with default settings except denoiser at 0.2-0.3. You can combine this LoRa with a lot of other Style / Attire / Pose / Acts LoRa, Also works well with character LyCoris.

Please leave a review if you have any critiques or if you find this LoRa good.

Sandalphon, Archangel of Diligence from the Seven Heavenly Virtues (Nanatsu no Bitoku). Includes character and 4 outfits that may be used on other characters.

Kohya LoCon trained on NAI. Seems to work well with any weight. Use high weight for animated style and low weight for realism.

Character trigger words:

• sandalphon - For character. Add "purple eyes, blue hair" for best results. Omit or use as negative prompt if applying outfits to different characters.

Outfit trigger words. Omit "sandalphon" keyword to use on other characters. (the source was extremely limited for most of these so milage may vary):

• sandalphonoutfit - For main outfit. Add "bare shoulders, headpiece, shield" for best results.

• sandalphongeneral - For general outfit. Add "hat, cape, leotard, mechanical arm" for best results.

• sandalphonred - For red riding hood/monster hunter outfit. Add "hood, red skirt, claws, gauntlet" for best results.

• sandalphonswimsuit - For swimsuit outfit.

My first lycoris. Works fine but sometimes it makes adult Groot

Can't wait to see your generations^^

Trained on SD 1.5 based model

About versions:

Ver 1.0: data set of 4 images, works fine

Ver 2.0: data set of 11 images, works sometimes worse and sometimes better than v1

Lora trained on Kunimitsu II from Tekken

Update:

new outfit and more possibilities to create custom outfits.

However, the original mask is less consistent, so I recommend using the old model for it

models used:

anime: CoffeeMix, PrimeMix

2,5D: ReV Animated, HELLmix, GlassBones, PsyGon Animerge - v1.1

realistic: fantasticmix_real, henmix_real

negative embeddings: embedding:bad-hands-5, embedding:ng_deepnegative_v1_75t, embedding:bad-artist, embedding:EasyNegative

Recommended settings:

• Make sure you are aware on the usage instructions of LORA

• VAE: vae-ft-mse-840000-ema-pruned, kl-f8-anime2, blessed2.vae (for anime models)

• Sampler: DPM++ SDE Karras or DPM++ 2M Karras

• Steps: 20

• Clipskip: 2

• Upscaler : img2img in comfyui using 4x-UltraMix_Smooth

• CFG Scale : 5 to 9 (mostly 7 and 8)

• LORA weight for txt2img: 0.5-1

• Denoise strength for img2img: 0.4 to 0.7

If you want the exact same settings, just drag and drop the picture into ComfyUI

for the pictures i used comfyui