CalicoMix Prisma✨ is the versatile model for high-resolution anime illustration, masterfully blending 2D purity with 2.5D depth. It excels at generating cute girl subjects across exciting genres, from the vibrant worlds of Fantasy and Magical Girls to the detailed mechanics of Sci-Fi, Mecha, and Mecha Musume.
"If you like my work, please support me on Ko-fi!"
This model is incredibly versatile, so feel free to generate whatever you love and enjoy!
*Just remember to be mindful of your audience before you share your creations.
Style prompt:
'anime screencap' for anime screencap/anime flat style
'realistic, photorealistic' for realistic style
Style influences can be adjusted using weights, such as:
(anime screencap:0.5)(realistic, photorealistic:0.5)(realistic, photorealistic:1.5)
More background focus:
use 'scenery'
recommends using rating prompts:
general > sensitive > questionable > explicit
use 'general' for SFW.
can add 'questionable' and 'explicit' at the same time to unlock max crazy lewdness.
can add 'questionable' and 'explicit' in the negative prompt to force more SFW.
Breast size control:
flat chest > small breasts > medium breasts > large breasts > huge breasts > gigantic breasts
can add breast size to the negative prompt.
can add multiple breast sizes for share effects between multiple tags.
can use weight to tone down breast sizes. eg. (large breasts:0.7)
Recommended Settings
Sampler: DPM++ 2M SDE (dpmpp_2m_sde_gpu), Euler, Euler A, DDIM
Scheduler: Karras, DDIM Uniform, AYS SDXL, Beta, Simple
Steps: 20-30
CFG Scale: 5.0 - 8.0
Clip Skip: 1 - 2
VAE: set to Auto to use included VAE
Resolution: various
Hires. Fix Settings (if necessary)
Upscaler: 4x Foolhardy Remacri, 4x UltraSharp, 4x AnimeSharp
Hires step: 10-15 (around half of the Steps, increase if it is too low details, decrease if it starts to generate duplicate objects like navel)
Denoising: 0.3-0.5 (More Denoising = More Makeup)
Hires scale: 2.0+
Recommended Prompt
masterpiece, best quality, very aesthetic, absurdres, newest,
Recommended Negative Prompt
worst quality, bad quality, low quality, lowres, scan artifacts, jpeg artifacts, sketch, signature, depth of field, blurry, blurry background, white background, simple background, fog, halo, bad hands, watermark
Description
First version
FAQ
Comments (9)
以前的CalicoMix EroILL系列跟Pony一樣霸道、放飛，在一些提詞上反應過度，變得較難預期，甚至底模的表情偶爾會壓過LoRA本身的效果，而非融合風格。反觀，這個CalicoMix Prisma系列很好控制，跟LoRA的風格搭配恰到好處，2025年，有很多使用者的審美觀已提升不少，尤其在Pixai平台上更明顯，更嚮往追求能超越過去的藝術作品。他們更希望模型的表現更趨近於精緻化，前提是誰訓練的模型更易於控制，而非像擲骰子一樣時好時壞，這模型應該可以滿足他們的需求。我覺得XYZ圖不是很能立刻看出差異在哪，但我可以看出背景中欄杆的構圖更正確，膚色更白皙，身材更苗條，飽和度更適中、更自然，這些都更能證明它的優越是藏在細節裏的。
谢谢您花时间写下这篇宝贵的评论。
您对Prisma控制力的认可，以及您提出的深刻见解，对我而言非常有价值。
Does it support native 2048x2048 or at least 1536x1536?
This model natively supports 1536x1536.
For resolutions of 2048x2048 or more, recommend using an Upscale and Hi-Res Fix
I don't think so. Looks like it's bases on some merges of Illustrious, which natively only has a vague support of vertical images like 1024x1536. It kinda supports 1536x1536 (like all other illustrious 0.1 - 2.0), but it breaks anatomy.
Thanks for posting your pics! I love seeing your creations. Keep generating and polishing. you're developing your style ✨
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.