Update README.md

README.md

@@ -1,3 +1,86 @@
 ---
+language:
+- en
+tags:
+- stable-diffusion
+- text-to-image
 license: creativeml-openrail-m
+inference: true
+pipeline_tag: text-to-image
 ---
+
+# i modelli 'Unico'
+
+<img  src=https://i.imgur.com/enQmrNJ.png
+width=100%  height=100%>
+Unico is the series of custom mixed models. Based on Inizio Unico and AbyssOrange2 models, and support .safetensors format only.
+
+[WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui)-amicable
+
+## Summary
+This model repository includes 5 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]().
+
+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 |
+| --- | --- | --- | --- | --- |
+| [AbyssOrange2 NSFW](https://huggingface.co/WarriorMama777/OrangeMixs) | Unico | 1, 0.9, 0.7, 0.5, 0.3, 0.1, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 0.1, 0.3, 0.5, 0.7, 0.9, 1 | 0 | *Unico Pera* |
+Unico Pera('Pear') is specialised to create Midjourney-like style.
+
+4.
+| Model: A | Model: B | U-Net Merge Weight | Base alpha | Merge Name |
+| --- | --- | --- | --- | --- |
+| [AbyssOrange2 NSFW](https://huggingface.co/WarriorMama777/OrangeMixs) | Unico | 1, 0.9, 0.7, 0.5, 0.3, 0.1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0.1, 0.3, 0.5, 0.7, 0.9, 1 | 0 | *Unico Cartamo* |
+Unico Cartamo('Safflower') is designed to unique mixing of semi-realistic with style of anime.
+
+5.
+| Model: A | Model: B | Merge Weight | Base alpha | Merge Name |
+| --- | --- | --- | --- | --- |
+| Unico Arancia | Unico Pera | weighted, M=0.5 | N/A | *Unico Castagna* |
+Unico Castagna('Chestnut') is the balanced model which has detail of Unico Arancia, tone of Unico Pera.
+
+6. 
+| Unico Castagna | AO2SFW-unicoarancia | add difference, M=0.5 | N/A | UC1
+| Unico Castagna | unicoarancia-unico | add difference, M=0.5 | N/A | UC2
+Currently in experiment
+
+## Recommend Settings
+- Prompt
+```
+#prompt format
+(sfw, masterpiece, best quality, extreme intricate detailed), (beautiful eyes and smooth radiant face, bishoujo), (/*place tags*/), (1 lady/*character tags*/), (/*colour of hair tag*/ hair, /*colour of eyes*/ eyes, thick lips, lip gloss), ((big breasts), (big pelvis), slim waist, long legs, pale skin, /*body tags*/), (/*clothing tags*/), (/*pose tags*/, alternate pose, octane render, very delicate cinematic light, colourful)
+
+#negative
+(worst quality, low quality:1.4), ((mutated hands and fingers:1.5), 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 five fingers(finger):1.5), (greater than 5 fingers per hand:1.5), less than 5 fingers per hand, (greater than five finger(fingers excluding thumb):1.5), fingers greater than 5, one hand with greater than 5 fingers, bad anatomy(finger)), (fat, chubby, curvy, 3d, realistic, watermark, signature, description, copyright), <bad_prompt_ver2>
+```
+- Variable 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)
+- Embedding:[bad_prompt_ver2](https://huggingface.co/datasets/Nerfgun3/bad_prompt/resolve/main/bad_prompt_version2.pt)
+- Clip Skip: 2
+- Resolution: 1024x576 w/ HighRes. Fix
+- HighRes. Fix: Latent(nearest-exact); upscale by 1.25
+
+## Sample Image
+
+>
+> <img src=https://i.imgur.com/s0KJuWX.jpeg
+> width=100%  height=100%>
+> ▲ X/Y Plot #1
+
+## 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
+*[email protected]* or [*Find Cinnamomo on Arcalive AI Art Channel*](https://arca.live/b/aiart)