AlekseyCalvin/Alexander_BLOK_Flux_LoRA_SilverAgePoets_v2_face_only

Alexander Blok Flux Low-Rank Adapter (LoRA) for SilverAgePoets.com

An adapter to reproduce the likeness of the legendary Symbolist/Modernist Russian and Soviet poet:
Alexander Blok (b.1880-d.1921)

CLICK HERE TO READ OUR TRANSLATION OF BLOK'S "STRANGER"/"NEZNAKOMKA"

This version of our Blok LoRA was the product of an experimental training to transfer face/attribute-features from historical photos with minimal compute time by using a high rank training, just short of a full model fine-tune, and a relatively high learning rate, but with a minimal number of steps.
This is the version from rank256 (if we recall correctly) and 250 steps.

As you can see, even 250 steps was far too many, as the resulting adapter lacks generalizability, and tries to make any prompt into a circa-21st century professional photo portrait.

On the flipside, it has arguably learned Blok's face (in his later life) somewhat better than our other versions.

Therefore, we've decided to still post it here.

Ideally, we ought to extract only the learned features into a much smaller-sized LoRA file.
As that would really shrink the file size and possibly aid with generalizability as well.
We will get around to doing that eventually.
For now, anyone interested in using this locally, please forgive for us the huge file size!

Prompt

BLOK_02.CR2, 1905, full height, a best quality color photo portrait of Alexander Blok writing a poem in 1905, curly hair, Edwardian coat

Trigger words

You should use BLOK_02.CR2 to trigger the image generation.

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_BLOK_Flux_LoRA_SilverAgePoets_v2_face_only', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers