---
language:
- en
tags:
- stable-diffusion
- text-to-image
license: creativeml-openrail-m
inference: true
pipeline_tag: text-to-image
---
# i modelli 'Unico'
Unico is the series of custom mixed models. Based on Inizio Unico and AbyssOrange2 models with U-Net Merge, and support .safetensors format only.
[WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui)-amicable
## Summary
This model repository includes 4 main models currently:
1.
| Model: A | Model: B | Merge Weight | Base alpha | Merge Name |
| --- | --- | --- | --- | --- |
| [Inizio Fantasma+Inizio Inseguitore+Inizio Foschia](https://huggingface.co/Cinnamomo/inizio) | [Inizio Replicante+Inizio Skinjob+Inizio Deckard](https://huggingface.co/Cinnamomo/inizio) | weighted, M=0.66666666+M=0.66666666 | N/A | *Unico* |
Unico is another form of [Inizio Unico](https://huggingface.co/Cinnamomo/inizio).
2.
| Model: A | Model: B | Merge Weight | Base alpha | Merge Name |
| --- | --- | --- | --- | --- |
| [Inizio Unico](https://huggingface.co/Cinnamomo/inizio) | [AbyssOrange2 SFW](https://huggingface.co/WarriorMama777/OrangeMixs) | weighted, M=0.75. | N/A | *Unico Arancia* |
Unico Arancia('Orange🍊') is the closest model from AbyssOrange2 SFW.
3.
| Model: A | Model: B | U-Net Merge Weight | Base alpha | Merge Name |
| --- | --- | --- | --- | --- |
| Unico Arancia | Elldreth 4060 | 1,0.9,0.7,0.5,0.3,0.1,0,0,0,0,0,0,0,0.2,0.2,0.2,0.2,0.2,0.2,0.1,0.3,0.5,0.7,0.9,1 | 0 | *Unico Arancia 2.0* |
Unico Arancia('Orange🍊') 2.0 is improved model of Unico Arancia.
4.
| Model: A | Model: B | U-Net Merge Weight | Base alpha | Merge Name |
| --- | --- | --- | --- | --- |
| (Unico Arancia+Unico Pera+Unico Cartamo+Unico Castagna+Unico Vaniglia) | (Elldreth 4060+SamDoesArtsUltMerge) | experimental mix | N/A | *Unico Castagna 2.0* |
Unico Castagna('Chestnut🌰') 2.0 is the improved model which focused to semi-realistic.
- NOTE: Another models are moved to legacy folder.
## Setting Reccomendation
```
##Basic prompts for anime
"txt2img/Prompt/value": "(best quality, extreme intricate detailed, beautiful eyes and smooth radiant face, bishoujo), (/*place tags*/), (1 girl/*character tags*/), (/*colour of hair tag*/ hair, /*colour of eyes*/ eyes, thick lips, lip gloss), (big breasts, big pelvis, slim waist, long legs, best ratio four finger and one thumb, /*body tags*/), (/*clothing tags*/), (/*pose tags*/, octane render, very delicate cinematic light, colourful)",
"txt2img/Negative prompt/value": "(nsfw, worst quality, low quality:1.5), (mutated hands and fingers, missing fingers, fused fingers, sharp fingers, interlocked fingers, abnormal fingers, too many fingers, mutated hand and finger, fusion finger, lose finger, multiple finger, bad detail(finger), bad anatomy(fingers), multiful(fingers), fused(fingers), greater than four fingers(finger), greater than 4 fingers per hand, less than 4 fingers per hand, greater than four finger(fingers excluding thumb), fingers greater than 4, one hand with greater than 4 fingers, bad anatomy(finger), cropped hands, extra digit, fewer digit:1.5), (fat, chubby, curvy, watermark, signature, description, copyright:1.5), (3d, realistic)"
```
- Variational Automatic Encoder: [SD MSE 840k.vae.safetensors](https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors)
- Clip Skip: 2
- Resolution: 1024x576 w/ HighRes. Fix
- HighRes. Fix: R-ESRGAN General WDN 4xV3; upscale by 1.25
## Sample Images
>
> width=100% height=100%>
> ▲ X/Y Plot #1
>
> width=100% height=100%>
>
> width=100% height=100%>
>
> width=100% height=100%>
>
> width=100% height=100%>
> ▲ Unico Arancia
## License Information
This model follows Creative ML Open RAIL-M: [Stable Diffusion License](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
But, You may use whatever you want. I don't like to set such restriction.
## Contact
*vitorriofungi@gmail.com* or [*Find Cinnamomo on Arcalive AI Art Channel*](https://arca.live/b/aiart)