README.md

metadata

license: creativeml-openrail-m
language:
  - en
base_model:
  - OnomaAIResearch/Illustrious-xl-early-release-v0
  - ChenkinNoob/ChenkinNoob-XL-V0.1
  - Menyu/noobaiXLNAIXL_epsilonPred11Version
tags:
  - art

A barebones repository for my base models.

Illustrious XL Series

MonsterCoffeeC4!

• Base Model: IllustriousXL v0.1 (SDXL 1.0)
• CivitAI Link
• Description: Focuses on semirealism.
• Recommended Settings
  • Positive Prompt: masterpiece, best quality, realistic
  • Negative Prompt: worst quality, low quality, jpeg artifacts, multiple views, 4koma, bad anatomy, bad hands, text
  • Sampler: Euler A Align Your Steps or DPM++ 2M SGM Uniform, 24 steps
  • Resolution: 832x1216 (Portrait) / 1216x832 (Landscape) / 1024x1024 (Square)
  • CFG Scale: 6
  • Hires: 2x-AnimeSharpV3, Upscaled by 1.5×, Denoise 0.3, 12 steps
• Models Merged
  • Madly Mix vol. IllustriousXL v2.0
  • Rillusm - Realistic Illustrious v1.1
  • Sade Abyss Style GLoRA
  • Zumidraws Style GLoRA

MonsterCoffeeVenom!

• Base Model: IllustriousXL v0.1 (SDXL 1.0)
• Arc en Ciel Link
• Description: Focuses on semirealism. Has a tendency to generate foreheads, likely having to do with the Rillusm checkpoint that was merged in.
• Recommended Settings
  • Positive Prompt: masterpiece, best quality, realistic
  • Negative Prompt (at minimum): worst quality, low quality
  • Sampler: Euler A Align Your Steps, 24 steps
  • Resolution: 832x1216 (Portrait) / 1216x832 (Landscape) / 1024x1024 (Square)
  • CFG Scale: 6
  • Hires: 2x-AnimeSharpV3, Upscaled by 1.5×, Denoise 0.3, 12 steps
• Models Merged
  • NoobAI-XL v1.1 Epsilon Pred
  • Rillusm - Realistic Illustrious v2.0
  • Sade Abyss Style GLoRA
  • Zumidraws Style GLoRA

MonsterCoffee5HourEnergy!

• Base Model: Chenkin Noob XL v0.1 (SDXL 1.0)
• CivitAI Link, Mirror
• Description: A blend comprising of semirealistic art styles. A VAE is already baked in.
• Recommended Settings
  • Positive Prompt: realistic, nose, lips
  • Negative Prompt (at minimum): worst quality, low quality
  • Sampler: Euler A Align Your Steps, 24 steps
  • Resolution: 832x1216 (Portrait) / 1216x832 (Landscape) / 1024x1024 (Square)
  • CFG Scale: 6
  • Hires: 2x-AnimeSharpV3, Upscaled by 1.5×, Denoise Strength: 0.3, 12 hires steps
• Models Merged
  • Chenkin Noob XL v0.1
  • Dandon Fuga Style GLoRA
  • Sciamano240 Style GLoRA
  • NeoArtCore Style GLoRA
  • Zumidraws Style GLoRA

    ---

MonsterCoffeeGhost!

• Base Model: Chenkin Noob XL v0.1 (SDXL 1.0)
• CivitAI Link, Mirror
• Description: A blend with a stylistic approach to 2D. A VAE is already baked in.
• Recommended Settings
  • Positive Prompt: masterpiece, best quality
  • Negative Prompt (at minimum): worst quality, low quality
  • Sampler: Euler A Align Your Steps, 24 steps
  • Resolution: 832x1216 (Portrait) / 1216x832 (Landscape) / 1024x1024 (Square)
  • CFG Scale: 6
  • Hires: 2x-AnimeSharpV4, Upscaled by 1.5×, Denoise Strength: 0.3, 12 hires steps
• Models Merged
  • Chenkin Noob XL v0.1
  • MLeth Style GLoRA
  • Tsuaii Style GLoRA
  • Kajinman Style GLoRA
  • Yatagarasupen Style GLoRA