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
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: DHANUSH

Tugce_Flux

Trained on Replicate using: https://replicate.com/ostris/flux-dev-lora-trainer/train

Trigger words

You should use tugce to trigger the image generation.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

# Load the model and LoRA weights
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('codermert/tugce2-lora', weight_name='flux_train_replicate.safetensors')

# Define different aspect ratios
aspect_ratios = [
    (512, 512),  # 1:1
    (768, 768),  # 3:3 (same as 1:1 but larger)
    (640, 512),  # 5:4
    (768, 512),  # 3:2
    (896, 512),  # 7:4
]

# Generate images for each aspect ratio
for width, height in aspect_ratios:
    image = pipeline(
        'tugce in a beautiful garden',
        width=width,
        height=height
    ).images[0]
    
    # Save the image
    image.save(f"tugce_{width}x{height}.png")
    print(f"Generated: tugce_{width}x{height}.png")

This code will generate images in various aspect ratios. You can modify the aspect_ratios list to include any desired dimensions.

Remember to use the trigger word tugce in your prompts to activate the LoRA model.

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers