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
tags:
- flux
- diffusers
- lora
- replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: illustration in the style of NWGMTRCPOPV01
widget:
- text: >-
a cat in a field of purple flowers, illustration in the style of
NWGMTRCPOPV01
output:
url: images/1.jpg
- text: >-
a girl wearing a flower crown, standing in a garden, illustration in the
style of NWGMTRCPOPV01
output:
url: extras/5.png
- text: >-
a cat taking a nap on a work table, illustration in the style of
NWGMTRCPOPV01
output:
url: images/3.jpg
- text: >-
a majestic beautiful flamingo, in a pink pond, illustration in the style
of NWGMTRCPOPV01
output:
url: images/4.jpg
- text: >-
a white-haired young woman wearing a flower crown, a very large fiery
dragon, castle in the background, illustration in the style of
NWGMTRCPOPV01
output:
url: extras/6.png
- text: >-
a big ferocious tiger, jungle, sunset, illustration in the style of
NWGMTRCPOPV01
output:
url: images/6.jpg
flux_geopop
Model description
Flux LoRA for creating geometrically styled illustrations. Use 'illustration in the style of NWGMTRCPOPV01' to trigger the model. Best with DEV (works well even with fp8). To use with flux1-dev-bnb-nf4 try increasing the LoRA strength (to say 1.3 and then adjust accordingly)
Trigger words
You should use illustration in the style of NWGMTRCPOPV01
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Training at Replicate
Trained at Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train