---
license: apache-2.0
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
- image-generation
- flux-diffusers
- diffusers
- photo
- realism
- Surrealism
- illustration
- experimental
- 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: >-
  ERNST style transposed layered illustration, Neurealist textographic photo collage
widget:
- text: >-
    RCA style agitprop poster, Neurealist textographic photo collage, MAYAK
    style art by Mayakovsky
  output:
    url: LifeOkay3.png
- text: >-
    film photograph portrait RCA style agitprop poster, Neurealist textographic
    photo collage, MAYAK style art by Mayakovsky
  output:
    url: LifeOkay2.jpg
- text: >-
    text: RCA style agitprop poster, Neurealist textographic photo collage,
    MAYAK style art by Mayakovsky
  output:
    url: RcaMakeLifeOkay1.png
- text: >-
    high definition award winning intricate dynamic photorealistic close up
    photo portrait of RCA style agitprop poster, Neurealist textographic photo
    collage, MAYAK style art by Mayakovsky
  output:
    url: MakeLifeCrop.jpg
- text: >-
    high definition award winning intricate dynamic photorealistic close up
    photo portrait of RCA style agitprop poster, Neurealist textographic photo
    collage, MAYAK style art by Mayakovsky
  output:
    url: images/example_joimmx505.png

---

# NEUREALLY TRANSPOSED COLLAGE FLUX LoRA for Posters, Illustrations, Book Covers, Collage art, Pamphlets, and more. By SilverAgePoets.com
An Experimental Repo where we will be testing out differently scale-coproportioned LoRA variants, each merged from two of our trained LoRAs. <br>
Namely: <br>
Our **Neurealist Collage II**^ LoRA (the de-distilled-FLUX-finetuned variant). <br> 
&
Our **Ernst's Transposed Surreal Collage**^ LoRA. <br> 

^: **Neurealist Collage II***: fine-tuned over Genova Apex Dedistilled on a dataset wherein each image constitutes a vertically tiled 1x1 collaging, intentionally/conceptually compiled by us from landscape-format screenshots of a certain YouTube doc (with caption fragments) entitled "Why Are We So Confused?". Prior to getting cross-stacked in dialectic relation to one another, each image was tactically and mostly manually (not just i2i, etc) modified/detourned by us in a variety of ways, into what we might obscurely call, say, prepost-DAnaDAish/metoomoderny (anti?)memes or something like that... <br> 
In short,  **Neurealist Collage II** LoRA was fine-tuned on vertically stacked screen-shape artworks with textboxed captions. <br> 

^^: **Ernst's Transposed Surreal Collage**:  fine-tuned over Genova Apex Dedistilled on a dataset wherein each image constitutes a landscape-shaped overlay of two illustrations, each constituting a page from **Max Ernst**'s pioneering 1934 surrealist textographic collage-novel [Une semaine de bonté ("A Week of Kindness")](https://en.wikipedia.org/wiki/Une_semaine_de_bont%C3%A9). <br>
In fact, these opacity-overlays are screenshots from a batch/auto-colorized version of a long GIF-image-sequence of Ernst book pages in a randomized order (with some repetitions), with simple opacity-cross-shifting overlay transitions between them. As we predicted, the colorization model (locally-run **DeOldify**, video-variant) reacted in totally different ways to the same two images overlayed with a different opacity ratio. <br>
The result of this was a vastly diversified range of aesthetic effects and chromatic qualities among the colorized frames. A selection from among these frames was then used by us as a fine-tuning dataset for the Ernst LoRA (or LoRAs, since it already exists in a few variants).   <br> 

## Trigger words
You should use `ERNST style transposed layered illustration` or/and `Neurealist textographic photo collage' to summon the poet's latent spirit.

## 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/AlekseyCalvin/NeureallyTransposedCollage_LoRA_bySilverAgePoets', weight_name='NeuroTransposedCollageLoRA_Scaled1.5_2.safetensors')
image = pipeline('your prompt').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)