![](images/R1486/logo.png)
# ▼ 本モデルの概要 (Overview of this model)
本モデルは
CreativeML OpenRAIL++-Mライセンスの訓練モデル、SDXL1.0追加学習モデル、またそれらのみをマージしたモデルを使用して製作されています。
VoidnoiseCoreXL R1486は、SDXL1.0モデルをベースにフォト調に調整し、SDXLの特徴である精細さを強く出したモデルになります。
SD1.xでは表現しきれなかった、出力の多様性も兼ね備えており、2.5D系の出力も崩れることなく出力できるモデルになっております。
This model will be a merged model, using only the training model and SDXL1.0 additional learning model from the
CreativeML OpenRAIL++-M license.
VoidnoiseCoreXL R1486 is based on the SDXL1.0 model, adjusted to a photo style, and has the strong definition characteristic of SDXL.
This model also has the versatility of output that SD1.x could not fully express, and is capable of outputting 2.5D output without any collapse.
# ▼ 推奨設定 (Recommended settings)
- Sampler: DPM++ SDE Karras
- Step: 30 - 35
- CFG scale: 8 - 10
- Denoising strength: 0.6 - 0.65
- Clip skip: 1
- Hires upscale: 1.5 - 2.0
- Hires steps: 15 - 18
- Hires upscaler: R-ESRGAN 4x+
- ENSD (Eta noise seed delta): 31337
- VAE: sdxl_vae
- Size: 1280 x 768 or 768 x 1280
# ▼ 出力サンプル (Sample)
[Prompt]
```
1 japanese woman,(27yo),cute,brown eyes ,catch light:, natural skin,brown hair, indoor ,light smile,thin formal dress
```
[Negative prompt]
```
(illustration:1.2),(anime:1.2),(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale),(watermark),
(white letters),signature,username,text,error,(manicure),(nsfw),(earing)
```
[Prompt]
```
1 japanese woman,(27yo),cute,brown eyes ,catch light:, natural skin,brown hair, indoor ,proud ,cardigan, tight jeans
```
[Negative prompt]
```
(illustration:1.2),(anime:1.2),(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale),(watermark),
(white letters),signature,username,text,error,(manicure),(nsfw),(earing)
```