Somov's C𝕒𝓇𝓃ⅈ𝓋𝔞𝓁esque 𝓛𝒾𝒶𝒾𝓼𝓸𝖓𝓼
HISTORIC 𝒜𝓡𝒯𝚒𝕤𝕥 STYLE ℒ𝓸ℜ𝐴𝘴
||| By SilverAgePoets.com |||
Note: These Variant III+.5/2 versions of this model, like the variant HERE, are a product of merging individual checkpoints from Variant/Training-Run III of this model. The merges here are simply the products of different checkpoints than the merge in the other Var3.5 repo.
In their turn, Variant III checkpoints (found HERE), the sources of these merges, were fine-tuned locally, on fewer artworks/samples & steps than Variants I & II, but with 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-fine-tuned CLIP/T5XXL.
Variant II checkpoints, found HERE, were fine-tuned at 64dim64alpha and over AfroMan4Peace's Colossus2.1_Dedistilled + LongCLIP-GmP-ViT-L-14 by zer0int.
Variant I checkpoints are found HERE: fine-tuned at 64dim128alpha and over DNA_1_618's Genova Apex De-distilled + LongCLIP-GmP-ViT-L-14 by zer0int.
A Low-Rank Adapter (LoRA) for FLUX-family models...
Fine-tuned on around 60 artworks inspired by Pierrot's lace tears, Columbina's satin gasps, Harlequin's velvet prances, by the toy moonlight of dreamed-up 18th centuries, and every achingly real rendezvous with fleeting masks of closeness...
And these artworks, of course, were crafted once upon a world by:
KONSTANTIN SOMOV (1869-1939), though representing but one facet, a brightest of dreams and among the deepest, of his manifold eclectic masteries.
Prompt with:
Scribble Somov style art, artwork by Konstantin Somov, detailed carnivalesque illustration & implore past-masked futures to guide you astray into endless carnival gardens; hedgerows tinseled with rainbows and moonglow, dresses & frock coats scuttle on echoes, rushing to catch for the billionth time early dawn fireworks of yearning igniting... Perhaps in these gardens you'd find at long last some mysteries yet to be dreamed...
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('AlekseyCalvin/Somov_Carnivalesques_V3.5Merged2_FluxLoRA_BySilverAgePoets')
image = pipeline('your prompt').images[0]