metadata

license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co./black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
  - en
pipeline_tag: text-to-image
library_name: diffusers
emoji: 🔜
tags:
  - flux
  - diffusers
  - lora
  - replicate
  - image-generation
  - flux-diffusers
  - schnell
  - photo
  - Mayakovsky
  - art
  - poster
  - realism
  - character
  - historical person
  - poetry
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: MAYAK style Constructivist Poster
widget:
  - text: >-
      MAYAK style drawing of politician saying /I AM CORRUPT!/, Constructivist
      cartoon poster
    output:
      url: MayakArtsV1_7.webp
  - text: >-
      MAYAK style drawing of politician saying /I AM CORRUPT!/, Constructivist
      cartoon poster
    output:
      url: MayakArtsV1_6.webp
  - text: >-
      MAYAK style drawing of politician saying /I AM CORRUPT!/, Constructivist
      cartoon poster
    output:
      url: MayakArtsV1_5.webp
  - text: >-
      MAYAK style drawing of politician saying /I AM CORRUPT!/, Constructivist
      cartoon poster
    output:
      url: MayakArtsV1_3.webp
  - text: >-
      MAYAK style drawing of politician saying /I AM CORRUPT!/, Constructivist
      cartoon poster
    output:
      url: MayakArtsV1_2.webp
  - text: >-
      MAYAK style drawing of politician saying /I AM CORRUPT!/, Constructivist
      cartoon poster
    output:
      url: MayakArtsV1_4.webp

Prompt
MAYAK style drawing of politician saying /I AM CORRUPT!/, Constructivist cartoon poster

Mayakovsky Style Soviet Posters & Cartoons Flux LoRA – Version 1 – by SOON®

Trained on Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train

Via Ostris' ai-toolkit on 50 high-resolution scans of 1910s/1920s posters & artworks by the great Soviet poet, artist, & Marxist activist Vladimir Mayakovsky.
For this training experiment, we first spent many days rigorously translating the textual elements (slogans, captions, titles, inset poems, speech fragments, etc), with form/signification/rhymes intact, throughout every image subsequently used for training.
These translated textographic elements were, furthermore, re-placed by us into their original visual contexts, using fonts matched up to the sources.
For this version of the training, unlike Version 2 (linked below), we used auto-captions, and did not train the text encoder.
This first not-very-successful version of the resultent LoRA (check out V.2 here) was trained on regular old FLUX.1-Dev.
This version of the training went for 1500 steps at a DiT Learning Rate of .0004, batch 3, with the Adamw8bit optimizer!
No synthetic data was used for the training!

This is a rank-32/alpha-32 Constructivist Art & Soviet Satirical Cartoon LoRA for Flux (whether of a Dev, a Schnell, or a Soon® sort...)

Check out our translations of Mayakovsky'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 MAYAK style Constructivist art 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/MayakArt', 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