Instructions to use BlueTriangles/SDXL_Magase_Ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BlueTriangles/SDXL_Magase_Ai with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OnomaAIResearch/Illustrious-XL-v2.0", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("BlueTriangles/SDXL_Magase_Ai") prompt = "\u0000\u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000S\u0000D\u0000X\u0000L\u0000_\u0000M\u0000a\u0000g\u0000a\u0000s\u0000e\u0000_\u0000A\u0000i\u0000_\u0000v\u00001\u0000:\u00000\u0000.\u00005\u0000>\u0000 \u0000(\u0000s\u0000d\u0000x\u0000l\u0000-\u0000m\u0000a\u0000g\u0000a\u0000s\u0000e\u0000-\u0000a\u0000i\u0000-\u0000y\u0000o\u0000u\u0000n\u0000g\u0000,\u0000 \u0000d\u0000a\u0000r\u0000k\u0000 \u0000b\u0000l\u0000u\u0000e\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000p\u0000o\u0000n\u0000y\u0000t\u0000a\u0000i\u0000l\u0000,\u0000 \u0000l\u0000o\u0000n\u0000g\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000p\u0000u\u0000r\u0000p\u0000l\u0000e\u0000 \u0000e\u0000y\u0000e\u0000s\u0000,\u0000 \u0000s\u0000m\u0000a\u0000l\u0000l\u0000 \u0000b\u0000r\u0000e\u0000a\u0000s\u0000t\u0000s\u0000,\u0000 \u0000s\u0000l\u0000e\u0000n\u0000d\u0000e\u0000r\u0000)\u0000,\u0000 \u0000(\u0000g\u0000e\u0000n\u0000e\u0000r\u0000a\u0000l\u0000,\u0000 \u00001\u0000g\u0000i\u0000r\u0000l\u0000,\u0000 \u0000s\u0000o\u0000l\u0000o\u0000,\u0000 \u0000a\u0000l\u0000o\u0000n\u0000e\u0000,\u0000 \u0000l\u0000o\u0000o\u0000s\u0000e\u0000 \u0000c\u0000l\u0000o\u0000s\u0000e\u0000-\u0000u\u0000p\u0000)\u0000,\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000P\u0000i\u0000n\u0000u\u0000p\u0000-\u0000I\u0000l\u0000l\u0000u\u0000s\u0000t\u0000-\u0000p\u00001\u0000:\u00000\u0000.\u00005\u0000>\u0000,\u0000 \u0000(\u0000s\u0000m\u0000i\u0000l\u0000e\u0000)\u0000,\u0000 \u0000(\u0000s\u0000c\u0000h\u0000o\u0000o\u0000l\u0000 \u0000u\u0000n\u0000i\u0000f\u0000o\u0000r\u0000m\u0000,\u0000 \u0000s\u0000e\u0000r\u0000a\u0000f\u0000u\u0000k\u0000u\u0000,\u0000 \u0000w\u0000h\u0000i\u0000t\u0000e\u0000 \u0000s\u0000h\u0000i\u0000r\u0000t\u0000,\u0000 \u0000b\u0000l\u0000a\u0000c\u0000k\u0000 \u0000c\u0000o\u0000l\u0000l\u0000a\u0000r\u0000,\u0000 \u0000r\u0000e\u0000d\u0000 \u0000n\u0000e\u0000c\u0000k\u0000t\u0000i\u0000e\u0000,\u0000 \u0000b\u0000l\u0000a\u0000c\u0000k\u0000 \u0000s\u0000k\u0000i\u0000r\u0000t\u0000,\u0000 \u0000p\u0000l\u0000e\u0000a\u0000t\u0000e\u0000d\u0000 \u0000s\u0000k\u0000i\u0000r\u0000t\u0000)\u0000,\u0000 \u0000(\u0000s\u0000i\u0000m\u0000p\u0000l\u0000e\u0000 \u0000b\u0000a\u0000c\u0000k\u0000g\u0000r\u0000o\u0000u\u0000n\u0000d\u0000,\u0000 \u0000b\u0000l\u0000a\u0000c\u0000k\u0000 \u0000b\u0000a\u0000c\u0000k\u0000g\u0000r\u0000o\u0000u\u0000n\u0000d\u0000}\u0000:\u00001\u0000.\u00005\u0000)\u0000,\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000i\u0000n\u0000g\u0000,\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000 \u0000s\u0000c\u0000r\u0000e\u0000e\u0000n\u0000c\u0000a\u0000p\u0000,\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000 \u0000s\u0000t\u0000y\u0000l\u0000e\u0000,\u0000 \u0000s\u0000o\u0000u\u0000r\u0000c\u0000e\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000,\u0000 \u0000f\u0000l\u0000a\u0000t\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000,\u0000 \u0000m\u0000a\u0000s\u0000t\u0000e\u0000r\u0000p\u0000i\u0000e\u0000c\u0000e\u0000,\u0000 \u0000b\u0000e\u0000s\u0000t\u0000 \u0000q\u0000u\u0000a\u0000l\u0000i\u0000t\u0000y\u0000,\u0000 \u0000a\u0000b\u0000s\u0000u\u0000r\u0000d\u0000r\u0000e\u0000s\u0000,\u0000 \u0000h\u0000i\u0000g\u0000h\u0000r\u0000e\u0000s\u0000,\u0000 \u0000v\u0000i\u0000b\u0000r\u0000a\u0000n\u0000t\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000s\u0000,\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000f\u0000u\u0000l\u0000,\u0000 \u0000c\u0000l\u0000e\u0000a\u0000r\u0000,\u0000 \u0000f\u0000i\u0000n\u0000e\u0000l\u0000y\u0000 \u0000d\u0000e\u0000t\u0000a\u0000i\u0000l\u0000e\u0000d\u0000)\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000d\u0000m\u0000d\u00002\u0000_\u0000s\u0000d\u0000x\u0000l\u0000_\u00004\u0000s\u0000t\u0000e\u0000p\u0000_\u0000l\u0000o\u0000r\u0000a\u0000:\u00000\u0000.\u00007\u0000>\u0000" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("OnomaAIResearch/Illustrious-XL-v2.0", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("BlueTriangles/SDXL_Magase_Ai")
prompt = "\u0000\u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000S\u0000D\u0000X\u0000L\u0000_\u0000M\u0000a\u0000g\u0000a\u0000s\u0000e\u0000_\u0000A\u0000i\u0000_\u0000v\u00001\u0000:\u00000\u0000.\u00005\u0000>\u0000 \u0000(\u0000s\u0000d\u0000x\u0000l\u0000-\u0000m\u0000a\u0000g\u0000a\u0000s\u0000e\u0000-\u0000a\u0000i\u0000-\u0000y\u0000o\u0000u\u0000n\u0000g\u0000,\u0000 \u0000d\u0000a\u0000r\u0000k\u0000 \u0000b\u0000l\u0000u\u0000e\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000p\u0000o\u0000n\u0000y\u0000t\u0000a\u0000i\u0000l\u0000,\u0000 \u0000l\u0000o\u0000n\u0000g\u0000 \u0000h\u0000a\u0000i\u0000r\u0000,\u0000 \u0000p\u0000u\u0000r\u0000p\u0000l\u0000e\u0000 \u0000e\u0000y\u0000e\u0000s\u0000,\u0000 \u0000s\u0000m\u0000a\u0000l\u0000l\u0000 \u0000b\u0000r\u0000e\u0000a\u0000s\u0000t\u0000s\u0000,\u0000 \u0000s\u0000l\u0000e\u0000n\u0000d\u0000e\u0000r\u0000)\u0000,\u0000 \u0000(\u0000g\u0000e\u0000n\u0000e\u0000r\u0000a\u0000l\u0000,\u0000 \u00001\u0000g\u0000i\u0000r\u0000l\u0000,\u0000 \u0000s\u0000o\u0000l\u0000o\u0000,\u0000 \u0000a\u0000l\u0000o\u0000n\u0000e\u0000,\u0000 \u0000l\u0000o\u0000o\u0000s\u0000e\u0000 \u0000c\u0000l\u0000o\u0000s\u0000e\u0000-\u0000u\u0000p\u0000)\u0000,\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000P\u0000i\u0000n\u0000u\u0000p\u0000-\u0000I\u0000l\u0000l\u0000u\u0000s\u0000t\u0000-\u0000p\u00001\u0000:\u00000\u0000.\u00005\u0000>\u0000,\u0000 \u0000(\u0000s\u0000m\u0000i\u0000l\u0000e\u0000)\u0000,\u0000 \u0000(\u0000s\u0000c\u0000h\u0000o\u0000o\u0000l\u0000 \u0000u\u0000n\u0000i\u0000f\u0000o\u0000r\u0000m\u0000,\u0000 \u0000s\u0000e\u0000r\u0000a\u0000f\u0000u\u0000k\u0000u\u0000,\u0000 \u0000w\u0000h\u0000i\u0000t\u0000e\u0000 \u0000s\u0000h\u0000i\u0000r\u0000t\u0000,\u0000 \u0000b\u0000l\u0000a\u0000c\u0000k\u0000 \u0000c\u0000o\u0000l\u0000l\u0000a\u0000r\u0000,\u0000 \u0000r\u0000e\u0000d\u0000 \u0000n\u0000e\u0000c\u0000k\u0000t\u0000i\u0000e\u0000,\u0000 \u0000b\u0000l\u0000a\u0000c\u0000k\u0000 \u0000s\u0000k\u0000i\u0000r\u0000t\u0000,\u0000 \u0000p\u0000l\u0000e\u0000a\u0000t\u0000e\u0000d\u0000 \u0000s\u0000k\u0000i\u0000r\u0000t\u0000)\u0000,\u0000 \u0000(\u0000s\u0000i\u0000m\u0000p\u0000l\u0000e\u0000 \u0000b\u0000a\u0000c\u0000k\u0000g\u0000r\u0000o\u0000u\u0000n\u0000d\u0000,\u0000 \u0000b\u0000l\u0000a\u0000c\u0000k\u0000 \u0000b\u0000a\u0000c\u0000k\u0000g\u0000r\u0000o\u0000u\u0000n\u0000d\u0000}\u0000:\u00001\u0000.\u00005\u0000)\u0000,\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000i\u0000n\u0000g\u0000,\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000 \u0000s\u0000c\u0000r\u0000e\u0000e\u0000n\u0000c\u0000a\u0000p\u0000,\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000 \u0000s\u0000t\u0000y\u0000l\u0000e\u0000,\u0000 \u0000s\u0000o\u0000u\u0000r\u0000c\u0000e\u0000 \u0000a\u0000n\u0000i\u0000m\u0000e\u0000,\u0000 \u0000f\u0000l\u0000a\u0000t\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000,\u0000 \u0000m\u0000a\u0000s\u0000t\u0000e\u0000r\u0000p\u0000i\u0000e\u0000c\u0000e\u0000,\u0000 \u0000b\u0000e\u0000s\u0000t\u0000 \u0000q\u0000u\u0000a\u0000l\u0000i\u0000t\u0000y\u0000,\u0000 \u0000a\u0000b\u0000s\u0000u\u0000r\u0000d\u0000r\u0000e\u0000s\u0000,\u0000 \u0000h\u0000i\u0000g\u0000h\u0000r\u0000e\u0000s\u0000,\u0000 \u0000v\u0000i\u0000b\u0000r\u0000a\u0000n\u0000t\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000s\u0000,\u0000 \u0000c\u0000o\u0000l\u0000o\u0000r\u0000f\u0000u\u0000l\u0000,\u0000 \u0000c\u0000l\u0000e\u0000a\u0000r\u0000,\u0000 \u0000f\u0000i\u0000n\u0000e\u0000l\u0000y\u0000 \u0000d\u0000e\u0000t\u0000a\u0000i\u0000l\u0000e\u0000d\u0000)\u0000 \u0000<\u0000l\u0000o\u0000r\u0000a\u0000:\u0000d\u0000m\u0000d\u00002\u0000_\u0000s\u0000d\u0000x\u0000l\u0000_\u00004\u0000s\u0000t\u0000e\u0000p\u0000_\u0000l\u0000o\u0000r\u0000a\u0000:\u00000\u0000.\u00007\u0000>\u0000"
image = pipe(prompt).images[0]Magase Ai / Babylon(曲世 愛 in バビロン)

- Prompt
- <lora:SDXL_Magase_Ai_v1:0.5> (sdxl-magase-ai-young, dark blue hair, ponytail, long hair, purple eyes, small breasts, slender), (general, 1girl, solo, alone, loose close-up), <lora:Pinup-Illust-p1:0.5>, (smile), (school uniform, serafuku, white shirt, black collar, red necktie, black skirt, pleated skirt), (simple background, black background}:1.5), anime coloring, anime screencap, anime style, source anime, flat color, masterpiece, best quality, absurdres, highres, vibrant colors, colorful, clear, finely detailed) <lora:dmd2_sdxl_4step_lora:0.7>

- Prompt
- <lora:SDXL_Magase_Ai_v1:0.5> (sdxl-magase-ai-young, dark blue hair, ponytail, long hair, purple eyes, small breasts, slender), (general, 1girl, solo, alone, bust shot), <lora:Pinup-Illust-p1:0.5>, (smile), (school uniform, serafuku, white shirt, black collar, red necktie, black skirt, pleated skirt), (simple background, green background}:1.5), anime coloring, anime screencap, anime style, source anime, flat color, masterpiece, best quality, absurdres, highres, vibrant colors, colorful, clear, finely detailed) <lora:dmd2_sdxl_4step_lora:0.7>

- Prompt
- <lora:SDXL_Magase_Ai_v1:0.5> (sdxl-magase-ai-young, dark blue hair, ponytail, long hair, purple eyes, small breasts, slender), (general, 1girl, solo, alone, loose close-up), (spontaneous), (embarrassed), (school uniform, serafuku, white shirt, black collar, red necktie, black skirt, pleated skirt), (simple background, white background}:1.5), anime coloring, anime screencap, anime style, source anime, flat color, masterpiece, best quality, absurdres, highres, vibrant colors, colorful, clear, finely detailed) <lora:dmd2_sdxl_4step_lora:0.7>

- Prompt
- <lora:SDXL_Magase_Ai_v1:0.7> (sdxl-magase-ai, dark blue hair, very long hair, purple eyes, mature female, medium breasts), (general, 1girl, solo, alone, cowboy shot), <lora:Pinup-Illust-p1:0.5>, (smile), (blue business suit, white shirt, pencil akirt, black stockings, black high heels), (simple background, pink background}:1.5), anime coloring, anime screencap, anime style, source anime, flat color, masterpiece, best quality, absurdres, highres, vibrant colors, colorful, clear, finely detailed) <lora:dmd2_sdxl_4step_lora:0.7>

- Prompt
- <lora:SDXL_Magase_Ai_v1:0.7> (sdxl-magase-ai, dark blue hair, very long hair, purple eyes, mature female, medium breasts), (general, 1girl, solo, alone, portrait), <lora:Pinup-Illust-p1:0.5>, (laughing), (blue business suit, white shirt, pencil akirt, black stockings, black high heels), (simple background, black background}:1.5), anime coloring, anime screencap, anime style, source anime, flat color, masterpiece, best quality, absurdres, highres, vibrant colors, colorful, clear, finely detailed) <lora:dmd2_sdxl_4step_lora:0.7>

- Prompt
- <lora:SDXL_Magase_Ai_v1:0.7> (sdxl-magase-ai, dark blue hair, very long hair, purple eyes, mature female, medium breasts), (general, 1girl, solo, alone, portrait), (sitting on steps), (innocent), (blue business suit, white shirt, pencil akirt, black stockings, black high heels), (simple background, grey background}:1.5), anime coloring, anime screencap, anime style, source anime, flat color, masterpiece, best quality, absurdres, highres, vibrant colors, colorful, clear, finely detailed) <lora:dmd2_sdxl_4step_lora:0.7>
Model description
せっかく作ったので公開していますが、@kageno さんの LoRA が遥かに高品質でキャラの描写も正確です。私が言うのも変ですが、@kageno さんの LoRA を強くお勧めします。
Appearance (young): sdxl-magase-ai-young, dark blue hair, ponytail, long hair, purple eyes, small breasts, slender, tareme
Appearance (mature): sdxl-magase-ai, dark blue hair, very long hair, purple eyes, medium breasts, mature female, tareme
Trigger words
You should use sdxl-magase-ai to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 7