Downloads · 30 days
169
18% of all-time downloads
AlekseyCalvin/EKSTERs_CONSTRUCTS_fluxLoRA_bySilverAgePoets
EKSTERs_CONSTRUCTS_fluxLoRA_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.
For generating stylized images reminiscent of iconic 1910s/1920s Constructivist avant-garde film/theatre stage set & costume designs by Aleksandra Ekster. <br
Downloads · 30 days
169
18% of all-time downloads
All-time downloads
953
Public
Repo size
178 MB
Likes
2
Public
Click a slice to open those files.
.safetensors172 MB · 95%
From the Hugging Face model README
For generating stylized images reminiscent of iconic 1910s/1920s Constructivist avant-garde film/theatre stage set & costume designs by Aleksandra Ekster. <br>
<Gallery />Our Low-Rank Adapter (LoRA) for FLUX models fine-tuned on a set of manually pre-processed & exhaustively captioned... <br> Selection of 45 scans of uncanny avant-garde Cubo-Futurist/Constructivist early-Soviet stage & costume design paintings & sketches by one of the 20th century's most iconic and impactful avant-garde artists: <br> Aleksandra Ekster (1882 — 1949), who had in her days on Earth (co-)formulated & defined the character of Eastern-European Cubo-Futurism, Suprematism, & Soviet Constructivism alike. <br>
PHOTO OF ALEKSANDRA EKSTER:

A few from among Ekster's stage designs used for this fine-tune:

A few from among Ekster's costume designs used for this fine-tune:

You should use Ekster style art or Ekster style art of a Constructivist theater set showing elaborate costumes or 'Ekster style stage set design art' or 'Ekster style Constructivist costume design art' to cast the artist's latent eye.
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/Theatre_Arts_and_Constructs_of_Aleksandra_Ekster_FLUXlora_by_SilverAgePoets')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers