metadata
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- merge
base_model:
- Raelina/Raehoshi-Illust-XL-2.1
- Laxhar/noobai-XL-0.75
NONAMEmix
Model Description
- Model type: Diffusion-based text-to-image generative model
- Model prompt style: Booru-tags
- License: Fair AI Public License 1.0-SD
V1.0:Base
V1.1:Modest in stature a little bit from base
V1.1_L:Very modest in stature from base
Merge Recipe
- Raehoshi illust XL 2.1 (A)
- NoobAI-XL Epsilon-Pred 0.75 (B)
- Movable Figure Model XL NOOB XL1.0 (C)
- paruparu illustrious v3.2 (D)
- SPO-SDXL_4k-p_10ep_LoRA_webui (E)
A + (C - B) * 0.2 + (D - B) * 0.5 + E = This Model v1.0
v1.0 + My LoRA(LECO) weight 1.0 + My LoRA(Muscle_XL_Ilst) weight -0.5 = v1.1
v1.0 + My LoRA(LECO) weight 3.0 + My LoRA(Muscle_XL_Ilst) weight -1.0 = v1.1_L
Recommended settings
- Positive prompts:
masterpiece, best quality, very aesthetic,
- Negative prompts:
lowres, bad quality, worst quality, very displeasing, bad anatomy, sketch, jpeg artifacts, signature, watermark,
- CFG: 5-6
- Sampling steps: 28
- Sampler: DPM++2M SDE
- Supported Resolution:
1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536
Hires.fix Setting
- Upscaler: [4x-UltraSharp]
- Hires step: 10-15
- Denoising: 0.3-0.4