metadata

license: apache-2.0
language:
  - en
tags:
  - flux
  - diffusers
  - lora
  - replicate
  - image-generation
  - flux-diffusers
  - diffusers
  - photo
  - realism
  - character
  - historical person
  - poetry
  - literature
  - history
  - archival
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
library_name: diffusers
emoji: 🔜
instance_prompt: AKHMATOVA, blemished skin texture with slight wrinkles
widget:
  - text: a close-up photo of AKHMATOVA
    output:
      url: AkhmatovaV3_1.png
  - text: >-
      film photograph portrait of a sad Anna Akhmatova in New York City, in her
      thirties, blemished skin texture with slight wrinkles
    output:
      url: AkhmatovaV3_2.png
  - text: >-
      vintage side-view photograph of young Anna AKHMATOVA, classic analog color
      photography
    output:
      url: AkhmatovaV3_3.png
  - text: >-
      text: "Annoyed, she threw cards to the wind!", a high quality poster of a
      very young thin poet Anna AKHMATOVA in 1910, sitting at a table outdoors
      and angrily throwing up into the air Tarot cards, inscription text: "She
      threw cards to the wind!"
    output:
      url: images/example_6dg8uypxo.png

Prompt
film photograph portrait of a sad Anna Akhmatova in New York City, in her thirties, blemished skin texture with slight wrinkles

Prompt
vintage side-view photograph of young Anna AKHMATOVA, classic analog color photography

Prompt
text: "Annoyed, she threw cards to the wind!", a high quality poster of a very young thin poet Anna AKHMATOVA in 1910, sitting at a table outdoors and angrily throwing up into the air Tarot cards, inscription text: "She threw cards to the wind!"

Prompt
high definition award winning intricate dynamic photorealistic close up photo portrait of anna akhmatova, in the background is planet earth covered with nuclear blasts, museum quality photography, background is a NATO-run highly decorated embassy jail, the composition is cinematic, the visual detail is intricate and graphic, intensive surreal and realistically dreamlike war imagery influenced by ilya kuvshinov, metahuman

Anna Akhmatova Flux Low-Rank Adapter (LoRA) Version 2 by SilverAgePoets.com

Trained via Ostris' ai-toolkit on 60 vintage photos (most of them colorized by us and/or by Klimbim).

And capturing the legendary poet:
Anna Andreevna Akhmatova
(b.06/26/1889-d.03/05/1966)

For this LoRA we used highly detailed manually-composed paragraph captions.

It was trained for 1200 steps at a Transformer Learning Rate of .0002, batch 1, AdamW8bit! Minimal synthetic data (just a few reluctant upscales), zero auto-generated captions!

VERSION 2 NOTE:

For this second version of an Akhmatova LoRA, we somewhat refined our dataset and used a tried-and-tested likeness-learning fine-tuning workflow over base FluxDev.
In parallel, we've also trained yet another Akhmatova LoRA over a homebrew De-Distilled merge version of Flux. That version is available in a different repo here.

MORE INFO:

This is a rank-24 historical LoRA for Flux (whether of a Dev, a Schnell, or a Soon® sort...)
Use it to diffusely diversify the presence of Akhmatova's deathless visage in our strange latter-day world! And once you're faced with this poet's iconic penetrating stare, do lend your ears to her as well: listen in to her voice! Wherefrom might this voice resound for you? A dusty paperback? Google search? Maybe a clip on YouTube? Or, say, your very memory reciting verses suddenly recalled?
In any case, we'll offer you some echoes to rely on, if you will: Namely, our translations of Akhmatova's verse-works, adapted from a proto-Soviet song-tongue into a Worldish one...
And found, along with many other poets' songs and tomes... Over at SilverAgePoets.com!

Trigger words

You should use AKHMATOVA or Anna Akhmatova or vintage autochrome photograph of Anna Akhmatova to summon the poet's latent spirit.

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/Akhmatova_Flux_LoRA_SilverAgePoets_v2_regularFluxD', 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