AlekseyCalvin
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -111,7 +111,7 @@ widget:
|
|
111 |
## ||| By SilverAgePoets.com |||
|
112 |
![Theatre](https://huggingface.co/AlekseyCalvin/Somov_GreatArtistStyle_FluxLoRA_bySilverAgePoets/resolve/main/Theatre.png)
|
113 |
*Note: **Variant III+.5** checkpoint(s) of this model, herein, are a product of merging individual checkpoints from **Variant/Training-Run III** of this model. <br>
|
114 |
-
In their turn, **Variant III** checkpoints (found [HERE](https://huggingface.co/AlekseyCalvin/Somov_Carnivalesques_V3_FluxLoRA_BySilverAgePoets)) were fine-tuned locally, on fewer artworks/samples & steps than **Variants I & II**, but
|
115 |
***Variant II** checkpoints, found [HERE](https://huggingface.co/AlekseyCalvin/Somov_Carnivalesques_V2_FluxLoRA_bySilverAgePoets), were fine-tuned at 64dim64alpha and over [AfroMan4Peace](https://civitai.com/user/Afroman4peace)'s [Colossus2.1_Dedistilled](https://civitai.com/models/833086?modelVersionId=996001) + [LongCLIP-GmP-ViT-L-14 by zer0int](https://huggingface.co/zer0int/LongCLIP-GmP-ViT-L-14).* <br>
|
116 |
***Variant I** checkpoints are found [HERE](https://huggingface.co/AlekseyCalvin/Somov_Carnivalesques_V1_FluxLoRA_BySilverAgePoets): fine-tuned at 64dim128alpha and over [DNA_1_618](https://civitai.com/user/DNA_1_618)'s [Genova Apex De-distilled](https://civitai.com/models/954608?modelVersionId=1068773) + [LongCLIP-GmP-ViT-L-14 by zer0int](https://huggingface.co/zer0int/LongCLIP-GmP-ViT-L-14).* <br>
|
117 |
|
|
|
111 |
## ||| By SilverAgePoets.com |||
|
112 |
![Theatre](https://huggingface.co/AlekseyCalvin/Somov_GreatArtistStyle_FluxLoRA_bySilverAgePoets/resolve/main/Theatre.png)
|
113 |
*Note: **Variant III+.5** checkpoint(s) of this model, herein, are a product of merging individual checkpoints from **Variant/Training-Run III** of this model. <br>
|
114 |
+
In their turn, **Variant III** checkpoints (found [HERE](https://huggingface.co/AlekseyCalvin/Somov_Carnivalesques_V3_FluxLoRA_BySilverAgePoets)) were fine-tuned locally, on fewer artworks/samples & steps than **Variants I & II**, but w/ higher peak lr (.0006), albeit periodized via cosine scheduling (working up to .0006 over 200 steps, then attenuating back down, before repeating the climb), at 64dim64alpha over Flux Dedistilled & regular non-tuned CLIP/T5XXL.* <br>
|
115 |
***Variant II** checkpoints, found [HERE](https://huggingface.co/AlekseyCalvin/Somov_Carnivalesques_V2_FluxLoRA_bySilverAgePoets), were fine-tuned at 64dim64alpha and over [AfroMan4Peace](https://civitai.com/user/Afroman4peace)'s [Colossus2.1_Dedistilled](https://civitai.com/models/833086?modelVersionId=996001) + [LongCLIP-GmP-ViT-L-14 by zer0int](https://huggingface.co/zer0int/LongCLIP-GmP-ViT-L-14).* <br>
|
116 |
***Variant I** checkpoints are found [HERE](https://huggingface.co/AlekseyCalvin/Somov_Carnivalesques_V1_FluxLoRA_BySilverAgePoets): fine-tuned at 64dim128alpha and over [DNA_1_618](https://civitai.com/user/DNA_1_618)'s [Genova Apex De-distilled](https://civitai.com/models/954608?modelVersionId=1068773) + [LongCLIP-GmP-ViT-L-14 by zer0int](https://huggingface.co/zer0int/LongCLIP-GmP-ViT-L-14).* <br>
|
117 |
|