Venere / README.md
Bern66's picture
Add generated example
656fd66 verified
|
raw
history blame
2.13 kB
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: VenereIA
widget:
  - text: >-
      VenereIA, a 20-year-old art student with stunningly beautiful features,
      visits  a gallery of modern art ,where there are some illuminating spots.
      Her cascading curly hair, subtly tinted with a slight shade of red, frames
      her brilliant blue eyes that seem to hold the depth of the ocean. Her
      ethereal beauty reminiscent of Botticelli's Venus demands attention. She
      wears a very elegant white nearly transparent cropped shirt  and black
      short  jeans. Her hands are visible.  She moves through the gallery and
      looks at a painting, smiling slightly. Capture her essence in an
      ultra-realistic full body portrait in an angle view bathed in sharp, vivid
      details and a bokeh effect that enhances her allure. Some of the art works
      are in the background. This high-contrast image bursts with colors and
      textures, creating a mesmerizing visual narrative fit for a prestigious
      photo magazine like the Vogue.
    output:
      url: images/example_qhercsfbz.png

Venere

Trained on Replicate using:

https://replicate.com/ostris/flux-dev-lora-trainer/train

Trigger words

You should use VenereIA to trigger the image generation.

Use it with the 🧨 diffusers library

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('Bern66/Venere', 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