This model is an experimental merge from various models, this model focus on natural and booru tag prompting, this model also has a semi-realistic features without the use of LoRA. I just built this model checkpoint to make a style i like nothing more, although this model hasn't been tested with LoRA's, im sure it can do a good mix with some LoRA's, this model is also good for making low steps images
_________________________________________________________________________________________________________
_______________________________________________
UPDATE 01/18/26
⚡ NOW SUPPORTS LOW STEPS (6 steps minimum) ⚡
🕛 DIFFERENT STYLES CFG 🕛
(2.5-3: SOFTER LOOK)
(4-6: DEFAULT AND CLASSIC LOOK)
(7+: MORE DEFINED AND CLARITY)
🌕 MORE DEFINED ANATOMY 🌕
NOW SUPPORTS DPMPP 2M KARRAS
FIXED EYE DETAILS (MEDIUM TO HIGH STEPS)
STYLE NOW HAS VARIETIES FOR CFG AND STEPS
NOW SUPPORTS LORA'S AT HIGH STRENGTH
_______________________________________________
⏾WHITE MOON⏾
⚪key features:
LORA-FREE MODEL: This model can generate high quality images without the use of adetailers or lora
BETTER ANATOMY: Can generate semi-perfect human figures and body shapes
🔞NSFW SUPPORT
⏾ ⋆.˚ CHARACTER SUPPORT
🎨🖌️DETAILED BACKGROUND: Clean and high quality background for prompt adherence
📖 VAE BAKED IN
_________________________________________________________________________________________________________
☪︎RECOMMENDED SETTINGS:
STEPS RECOMMENDED: 20-30 steps for better results, 8-16 for soft vibes
CFG: 3-5
● I use 3.5-4.5, it is the best CFG for the balance of creativity and prompt adherence in the model especially if you want a creative look while maintaining the quality
SAMPLER: DPMPP 2M SDE (or DPM++ 2M on CIVITAI), DPMPP 2M, EULER ANCESTRAL
SCHEDULER: Karras (best paired with Euler A), Normal, SGM Uniform (Best paired with DPM samplers)
RESOLUTION: Any resolution does well with this model except for huge landscape resolution with distant views. It can also do 512x512, 1024x1024, and up to 1536x1536 without breaking.
●RECOMMENDED RESOLUTIONS:
1024 x 1024
1152 x 896
896 x 1152
1216 x 832
832 x 1216 (most recommended)
1344 x 768
768 x 1344
1536 x 640
640 x 1536
RECOMMENDED POSITIVE: masterpiece, best quality, absurdres, hires, high quality
RECOMMENDED NEGATIVE: worst quality, low quality, lowres
_________________________________________________________________________________________________________
Please do share feedbacks for improvement in this model, suggestions and criticism will be openly accepted ⏾⋆
_________________________________________________________________________________________________________
License & Use
SDXL - CreativeML Open RAIL++-M
Illustrious - https://freedevproject.org/faipl-1.0-sd/
NoobAI-XL - https://civarchive.com/models/license/1140829
Copied the above license list from Plant Milk's page.
Description
FAQ
Comments (2)
This Model is a bit unstable for dpmpp 2m, and im currently working on it to better improve the model's function in other samplers
New version now works with dpmpp 2m and shouldn't have any problem now, it also works with fewer steps to save up energy and cost for on-site users


















