Downloads · 30 days
60
5% of all-time downloads
AlekseyCalvin/NikolayKupreyanov_FluxLoRA_v1_bySilverAgePoets
NikolayKupreyanov_FluxLoRA_v1_bySilverAgePoets is a text-to-image model from AlekseyCalvin. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
FIND OUR ALTERNATE (FLUX-Dedistilled-finetuned) VARIANT OF THIS LoRA AT THIS LINK. THIS VARIANT OF OUR KUPREYANOV ART STYLE LoRA was tuned over a base Dev version of FLUX.1, at a lower rank, but higher step count than…
Downloads · 30 days
60
5% of all-time downloads
All-time downloads
1.2K
Public
Repo size
172 MB
Likes
2
Public
Click a slice to open those files.
.safetensors172 MB · 98%
From the Hugging Face model README
FIND OUR ALTERNATE (FLUX-Dedistilled-finetuned) VARIANT OF THIS LoRA AT THIS LINK. THIS VARIANT OF OUR KUPREYANOV ART STYLE LoRA was tuned over a base Dev version of FLUX.1, at a lower rank, but higher step count than Variant 2.
Our Low-Rank Adapter (LoRA) for FLUX models fine-tuned on a set of manually pre-processed & exhaustively captioned art scans... <br>
Representing a small selection (30 pieces) from the distinctive oeuvre of woodcuts, etchings, engravings, drawings, & poster designs by: <br>
the artist/engraver Nikolay Nikolayevich Kupreyanov (1894 — 1933), one of the iconic avant-garde formulators of c.1910s-1920s early Soviet visual culture. <br>

For generating stylized images resembling early-Soviet Suprematism-influenced woodcuts, drawings, & designs for posters, ex-libris, & more. <br>
<Gallery />Check out a gallery of source woodcuts by Nikolay Kupreyanov here. <br>
Most of the images found at the above link were used by for this fine-tune (alongside further sources, such as sampling of Kupreyanov's agitprop poster designs). <br>
You should use Nikolay Kupreyanov woodcut etching style illustration or 'Kupreyanov style art' to summon the artist's latent hand.
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/NikolayKupreyanov_FluxLoRA_v1_bySilverAgePoetsd', weight_name='NikolayKupreyanov_FluxLoRA_v1_bySilverAgePoets.safetensors')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers