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: CONTTOK
widget:
  - text: >-
      This image showcases a modern, two-story house with a contemporary
      architectural design. The structure features a clean, white facade
      complemented by stone-textured accents that add a touch of natural
      elegance. Large windows allow ample natural light to filter into the
      interiors, while sleek, horizontal railings adorn the spacious balconies
      and rooftop terrace. The house is surrounded by lush greenery, including
      potted plants and a well-maintained garden. The front entrance is marked
      by wooden doors, and a carport is neatly integrated into the layout,
      providing shelter for vehicles. Warm lighting fixtures on the exterior
      walls create a welcoming ambiance, enhancing the house's visual appeal
      during the evening. This design offers a luxurious yet cozy atmosphere,
      ideal for a family residence with five bedrooms and three bathrooms.
    output:
      url: images/example_voziii3sc.png

Flux.1 Dev Lora Container

Trained on Replicate using:

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

Trigger words

You should use CONTTOK 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('KalaniP/flux.1-dev-lora-container', 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