metadata

license: apache-2.0
tags:
  - text-to-image
  - template:sd-lora
  - flux
  - lora
  - flux schnell
  - image-generation
  - diffusers
  - photo
pipeline_tag: text-to-image
emoji: 🔜
language:
  - en
base_model: black-forest-labs/FLUX.1-schnell
instance_prompt: LEN Vladimir Lenin
widget:
  - text: >-
      LEN Vladimir Lenin menacingly shaking his fist with a smirk, backdrop of
      San Francisco in 2003
    output:
      url: Len1.png
  - text: >-
      LEN Vladimir Lenin menacingly shaking his fist at the Eiffel Tower with a
      smirk, backdrop of Paris
    output:
      url: Len2.png

Soonr Flux HST V: SCHNELLenin

A realistic Vladimir Lenin LoRA for FLUX.1-schnell. Trained by me (aka A.C.T. Soon®) for 2000 steps on one A100 via Colab Pro, using the dedicated Schnell Training Notebook by Ostris on 30 colorized photographs of Vladimir Ilyich Lenin taken between 1918 and 1923. Some of the colorizations were done by Klimbim, others by me.

Prompt
LEN Vladimir Lenin menacingly shaking his fist with a smirk, backdrop of San Francisco in 2003

Prompt
LEN Vladimir Lenin menacingly shaking his fist at the Eiffel Tower with a smirk, backdrop of Paris

Trigger words

You should use LEN or 'LEN Vladimir Lenin' to trigger the image generation. Adding Lenin's name should further reinforce the training, bridging the inference to whatever scraps of historical personage awareness had made it into the base model. (Do not do this during training, however!)

base model: black-forest-labs/FLUX.1-schnell
training adapter for Schnell: ostris/FLUX.1-schnell-training-adapter