Alexander Apsit FLUX LoRA for Posters, Illustrations, Book Covers, Collage art, Pamphlets, and more. By SilverAgePoets.com
Our Low-Rank Adapter (LoRA) for FLUX models, fine-tuned on the distinctive c.1910s-1920s early Soviet poster illustrations by:
the artist Alexander Apsit (1880-1944).
Trained via LiuLiu's PEFT+Tensorflow-based trainer built into the DrawThings app.
Cosine annealing scheduling with warm restarts.
Only 3 epochs, 600 steps, but 128 dims/alpha, with orthogonal down layer fixing.
Trigger words
You should use APSIT style or 'APSIT style Soviet revolutionary illustration' to summon the artist's latent hand.
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/Alexander_Apsit_Style_Art_FLUX_LoRa_By_SilverAgePoets_DrawThingsTrainedOnDeDistilled', weight_name='VaApsit_lora_600st_f16convert.safetensors')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers