---
license: apache-2.0
language:
- en
base_model:
- black-forest-labs/FLUX.1-dev
tags:
- lora
- flux
- diffusers
- image-generation
pipeline_tag: text-to-image
library_name: diffusers
instance_prompt: photo of Julian Assange, white hair, realistic Assange
widget:
- text: >-
    photo of julian assange, amateur color photo of Julian Assange in the
    streets of San Francisco circa 1960, terrorizing and unnerving 1960
    passersby, Captioned with text: "Assange was traveling thru time", textured
    surfaces, blemished textured skin with pores
  output:
    url: images/example_m76g8g9v1.png
- text: >-
    Photos of Julian Assange  a textographic collage featuring two distinct
    sections or segments: section '1':  The upper section shows a photograph of
    Julian Assange in a suit, set against a vivid background with swirling
    clouds.   section '2': The bottom section features a photo of Julian Assange
    all agape with panic (his appearance adapted from Munsch's famous painting
    "The Scream”, which the collage's bottom section ‘2’ resembles).  In '2' the
    subject screams amid a huge garden of building-like 3D obelisks, a surreal
    landscape of jagged, colorful forms.
  output:
    url: images/example_jn8ko9axt.png
- text: >-
    Photo of young Julian Assange looking through a hole razored out of a book,
    amateur film camera photograph, blueish eyes, realistically textured skin
    with pores, realistic young Assange, white hair
  output:
    url: images/example_xifa7cskg.png
- text: >-
    (Merge2ckpt) Photos of Julian Assange  a textographic collage featuring two
    distinct sections or segments: section '1':  The upper section shows a
    photograph of Julian Assange in a suit, set against a vivid background with
    swirling clouds.   section '2': The bottom section features a photo of
    Julian Assange all agape with panic (his appearance adapted from Munsch's
    famous painting "The Scream”, which the collage's bottom section ‘2’
    resembles).  In '2' the subject screams amid a huge garden of building-like
    3D obelisks, a surreal landscape of jagged, colorful forms.
  output:
    url: images/example_2vv4n0gtg.png
- text: >-
    (Merge3ckpt) photo of julian assange, amateur color photo of Julian Assange
    in the streets of San Francisco circa 1960, terrorizing and unnerving 1960
    passersby, Captioned with text: "Assange was traveling thru time", textured
    surfaces, blemished textured skin with pores
  output:
    url: images/example_alh345a1t.png

---
## Julian Assange ℒ𝓸ℜ𝐴 Variant 2.5
## |||| By SilverAgePoets.com ||||
*NOTE: This Variant was fine-tuned over a Dedistilled version of Flux, at a higher rank than Var. 1.* <br>
*This further modification of Variant 2 is a convolution-style merge of two checkpoints from the second training.* <br>
*Find **Julian Assange LoRA Variant 1** [HERE](https://huggingface.co/AlekseyCalvin/Julian_Assange_FluxLoRA_BySilverAgePoets).* <br>

A Low-Rank Adapter (LoRA) for FLUX-family models... <br>
Intended to produce the likeness of Julian Assange circa roughly 2014-2017. <br>
Made to create content for a conceptual animation project. <br>
This LoRA was fine-tuned on a minimal set of widely available publicity photos, many (if not all) of which have almost certainly already gone into SD1.4/1.5 and maybe other models (albeit in unfocused-on forms), via news/etc-sourced pre-training data. <br> 
We politely ask you not to use this LoRA towards any creation, production, illustration, or any other use-case that might in any way compromise (or even so much as annoy) the real Assange. <br>

<Gallery />

## Prompt using:
`Photo of Julian Assange, white hair, realistic Assange`, etc...  <br>

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
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/Julian_Assange_Var2.5_MergedCkptsOverDedist_FluxLoRA_BySilverAgePoets')
image = pipeline('your prompt').images[0]
```