README.md

---
license: other
license_name: faipl-1.0-sd
license_link: https://freedevproject.org/faipl-1.0-sd/
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
tags:
- text-to-image
- stable-diffusion
- stable-diffusion-xl
- merge
base_model:
- Raelina/Raehoshi-illust-XL-3
- Laxhar/noobai-XL-Vpred-0.6
---

<style>
.gallery {
  display: grid;
  grid-template-columns: repeat(3, 1fr);
  gap: 10px;
}

.gallery img {
  width: 100%;
  height: auto;
  margin-top: 0px;
  margin-bottom: 0px;
  border-radius: 10px;
  box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
  transition: transform 0.3s;
}
</style>

# NONAMEmix-Vpred

## NOTICE
- This is a v-prediction model.
- Plz read "How to Use the Model" section on [NoobAI-XL model page](https://civitai.com/models/833294).
- Problem that not detected as a v_pred model is fixed.

<div class="gallery">
  <img src="./sample01.webp" alt="sample_v11_1">
  <img src="./sample02.webp" alt="sample_v11_2">
  <img src="./sample03.webp" alt="sample_v11_3">
</div>

## Model Description
- **Model type**: Diffusion-based text-to-image generative model
- **Model prompt style**: Booru-tags
- **License**: [Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)

## Merge Recipe
- Raehoshi illust XL 3.0 (A)
  - (https://civitai.com/models/846917/raehoshi-illust-xl)
- RouWei 0.6.1 vpred (B)
  - (https://civitai.com/models/950531/rouwei)
- paruparu illustrious v3.2 (C)
- NoobAI-XL Epsilon-Pred 0.75 (D)
- NoobAI-XL Epsilon-Pred 1.1 (E)
  - (https://civitai.com/models/833294?modelVersionId=998979)
- SPO-SDXL_4k-p_10ep_LoRA_webui (F)
  - (https://civitai.com/models/510261/spo-sdxl4k-p10eplorawebui)
```
A + (C - D) * (0.2,0.2,0.3,0.2,0.3,0.3,0.7,0.3,0.2,0.2,0.2,0.2,0.3,0.3,0.2,0.2,0.5,0.3,0.2) = G
B + (G - E) * (0,0.2,0.7,0.3,0.5,0.5,0.7,0.2,0.3,1,0.2,0.2,0.7,0.2,0.2,0,0.7,0.2,0.3) = H
H + F * weight 1.0 = This Model v1.1
```

## 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:** 3-5
- **Sampling steps:** 28
- **Sampler:** Euler a
- **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

## License

[Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)