---
license: apache-2.0

language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "AlekseyCalvin/Colossus_2.1_dedistilled_by_AfroMan4peace"
pipeline_tag: text-to-image
# widget:
#   - text: >-
#       prompt
#     output:
#       url: https://...
instance_prompt: ROSA Fluxenburg

widget:
- text: >-
    A photo of the revolutionary ROSA Fluxenburg as a punk in London 1980s
  output:
    url: RosaBrit4.webp
- text: A photo of the revolutionary ROSA Fluxenburg as a punk in London 1980s
  output:
    url: RosaBrit2.webp
- text: >-
    A photo of the revolutionary ROSA Fluxenburg...
  output:
    url: RosaWillRise.png
---
<Gallery />

# ROSA LUXEMBURG FLUXenburg Low-Rank Adapter (LoRA) V.2

The great revolutionary rises from under sea!
Meet face-to-face a reincorporealized and (within your own spirit) resurrected visionary pioneer & hero of the classless future, and a martyr for the its cause, now becoming revitalized everyplace!

**Click over to YouTube** via [this exclusive link](https://youtu.be/P6-BRSNHLhU?si=7yUjNn8yGpqDlrOg) to watch **LIVING UNDER C.**: our little musical film starring many versions of **Rosa Luxenburg**, and of others besides. The film includes several songs, much archival footage and imagery re-interpreted by trained models, synthetic singing, real minimally processed singing, quotes from political theory and from poetry, and much else! <br>

It seems this LoRA, trained on the **Colossus 2.1 Dedistilled Flux trained+merged model by AfroMan4Peace**, available [here](https://huggingface.co/AlekseyCalvin/Colossus_2.1_dedistilled_by_AfroMan4peace) in a diffusers format and [here at CivitAI](https://civitai.com/models/833086/colossus-project-flux), could be used fairly well with any version of FLUX. 
Inference on Schnell-based models seems to work better with this adapter than with any identity-transferring LoRA's we've tried that were trained on a distilled Flux Dev.

<!-- <Gallery /> -->


## Trigger words
You should use `ROSA Fluxenburg` to trigger the image generation.


## 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/Rosa_FLUXenburg_LoRA_v2_Dedistilled-Trained_SilverAgeLiberators', 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](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)