---
license: cc0-1.0
tags:
  - stable-diffusion
  - text-to-image
---

----
## -Specializing in Japanese girls Test Model
## -Merged photo-real model mixed 1000+ Twitter images.


for Stable Diffusion Webui Automatic1111</br>
type: .safetensors(ckpt)</br>
CFG Scale: middle-low</br>

## Negative prompts are rarely needed.
example.</br>
low quality, worst quality, bad anatomy, bad proportions

## Recommended VAE
vae-ft-mse-840000-ema-pruned


----

# El Zipang_test1.4
-The composition and the human body are even less fragile. Maybe...

[test_no_zipang.safetensors](https://huggingface.co/deadman44/SD_Photoreal_Merged_Models/resolve/main/test_no_zipang.safetensors) + [El Zipang_test1.3.safetensors](https://huggingface.co/deadman44/SD_Photoreal_Merged_Models/resolve/main/El%20Zipang_test1.3.safetensors) -> Simple Merge!!!

----

# El Zipang_test1.3
[Download](https://huggingface.co/deadman44/SD_Photoreal_Merged_Models/resolve/main/El%20Zipang_test1.3.safetensors)<br/>
-Just changed the block-weighted merge ratio.<br/>
-Better hands and better poses than 1.0. Maybe...<br/>
thanks, supermerger!!!<br/>
http://github.com/hako-mikan/sd-webui-supermerger/<br/>

[<img src=https://i.imgur.com/GyKs8Up.png  style="max-width: 128px;" width="25%" />](https://i.imgur.com/GyKs8Up)
[<img src=https://i.imgur.com/sXnAGF8.png  style="max-width: 128px;" width="25%" />](https://i.imgur.com/sXnAGF8)
[<img src=https://i.imgur.com/zE77vws.png  style="max-width: 128px;" width="25%" />](https://i.imgur.com/zE77vws)


----

# El Zipang_test1.0(test01)
[Download](https://huggingface.co/deadman44/SD_Photoreal_Merged_Models/resolve/main/El%20Zipang_test01.safetensors)<br/>
- Photo-Real</br>
photo realistic:+++++</br>
portrait:+++++</br>
artistic:+</br>
action:+</br>
hand:+</br>

[<img src=https://i.imgur.com/MK6MUu0.png  style="max-width: 128px;" width="25%" />](https://i.imgur.com/MK6MUu0)[<img src=https://i.imgur.com/HmSC45w.png  style="max-width: 128px;" width="25%" />](https://i.imgur.com/HmSC45w)[<img src=https://i.imgur.com/Qs1DJyS.png  style="max-width: 128px;" width="25%" />](https://i.imgur.com/Qs1DJyS)[<img src=https://i.imgur.com/G0KhpMu.png   style="max-width: 128px;" width="25%" />](https://i.imgur.com/G0KhpMu)[<img src=https://i.imgur.com/wk69lFK.png   style="max-width: 128px;" width="25%" />](https://i.imgur.com/wk69lFK)[<img src=https://i.imgur.com/dYG6xTp.png   style="max-width: 128px;" width="25%" />](https://i.imgur.com/dYG6xTp)

## example
<img src=https://i.imgur.com/KuWcOxX.png>

```jsx
japanese, 1girl, solo, looking at viewer, long hair, couch, black hair, smile, realistic, bangs, long sleeves, black eyes, brown eyes, upper body, sitting, fingernails, lips, school uniform, closed mouth
Negative prompt: low contrast, lowers, normal quality, low quality, worst quality, bad anatomy, bad proportions
Steps: 10, Sampler: DPM++ SDE Karras, CFG scale: 5, Seed: 185236819, Size: 512x768, Model hash: c785dff0
```
-Recommended prompt:
```jsx
japanese, realistic, 1girl, 
Negative prompt:
normal quality, low quality, worst quality, bad anatomy, bad proportions, 
CFG scale: 4-8
```
----