coundia / README.md
pcoundia's picture
Add generated example (#3)
930df06 verified
|
raw
history blame
3.34 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: LORACOUNDIA01
widget:
  - text: >-
      A close-up portrait of a LORACOUNDIA01 as a dashing and elegant Santa
      Claus, radiating charm and joy in a Senegalese festive setting. Their face
      is adorned with a neatly groomed, fluffy white beard, complementing a
      warm, welcoming smile. They wear a vibrant red and gold boubou,
      exquisitely detailed with intricate embroidery, giving a regal and festive
      appearance. A sleek Santa hat, designed with matching red and gold fabric,
      sits perfectly on their head, tilted just slightly for a touch of
      playfulness.  The background glows with the warmth of a golden sunset over
      a bustling Senegalese village, where baobab trees are decorated with
      strings of colorful lights and ornaments. Children in bright, traditional
      outfits surround the scene, their faces beaming with excitement as they
      gather to receive gifts. LORACOUNDIA01 holds a beautifully wrapped
      present, their pose exuding generosity and festive cheer. This enchanting
      portrait blends the magic of Christmas with the rich culture and vibrant
      colors of Senegal, creating a truly unique and heartwarming vision of a
      modern, elegant Santa Claus.
    output:
      url: images/example_loyqsoxqz.png
  - text: >-
      LORACOUNDIA01, a full-body artwork in the iconic Grand Theft Auto (GTA)
      style, showcasing a confident man standing in a bold pose. He is dressed
      in casual yet stylish clothing: a black leather jacket over a white
      t-shirt, paired with dark jeans and clean sneakers. His expression is cool
      and composed, with a slight smirk that exudes charisma. The setting is an
      urban street scene at sunset, with graffiti-covered walls, parked cars,
      and neon-lit shop signs in the background. The composition features clean,
      sharp outlines, bold colors, and a slightly exaggerated, cel-shaded
      aesthetic characteristic of GTA cover art. The focus remains on the
      character, with dynamic lighting that adds depth—highlighting the edges of
      his outfit and face for a dramatic effect. The background is vibrant yet
      minimally detailed to ensure the subject stands out as the focal point.
    output:
      url: images/example_33eilr7gn.png

Loracoundia01

Prompt
a man , LORACOUNDIA01, a minimalistic and stylized illustration of yourself. The focus is on clean lines and soft details, highlighting your sharp features and confident expression. Dressed in a casual yet sleek outfit, the portrait emphasizes approachability and authenticity. The background is simple and neutral, with subtle gradients or textures to enhance the overall composition without overpowering the subject. The style is light, modern, and expressive, capturing your essence in a straightforward yet visually appealing way.

Trained on Replicate using:

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

Trigger words

You should use LORACOUNDIA01 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('pcoundia/loracoundia01', 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