metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - lora
  - template:sd-lora
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      sketch, modern architectural design with a serene pond in the foreground,
      minimalist style, flat roof structures, greenery integration, soft color
      palette with greens and light blues, people walking, low angle shot, glass
      and concrete materials, hand-drawn coloring technique, subtle shading,
      balanced composition, depth with layering, realistic textures,
      proportional layout, peaceful and natural ambiance.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

simpletuner-lora

This is a LyCORIS adapter derived from black-forest-labs/FLUX.1-dev.

The main validation prompt used during training was:

sketch, modern architectural design with a serene pond in the foreground, minimalist style, flat roof structures, greenery integration, soft color palette with greens and light blues, people walking, low angle shot, glass and concrete materials, hand-drawn coloring technique, subtle shading, balanced composition, depth with layering, realistic textures, proportional layout, peaceful and natural ambiance.

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolution: 1024x1024

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

Prompt
unconditional (blank prompt)

Negative Prompt
blurry, cropped, ugly

Prompt
modern architecture, canopy structures, white material, urban design, outdoor space, trees, landscaping, seating areas, people, daylight, clear sky, recreational area, paving pattern, public area, contemporary design, pergola-like elements, radial pattern, greenery, mixed-use space

Negative Prompt
blurry, cropped, ugly

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

Training epochs: 148
Training steps: 4900
Learning rate: 0.0001
Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
Precision: bf16
Quantised: No
Xformers: Not used
LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 16,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

sktech_dataset

Repeats: 0
Total number of images: 33
Total number of aspect buckets: 1
Resolution: 0.147456 megapixels
Cropped: True
Crop style: center
Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
wrapper.merge_to()

prompt = "sketch, modern architectural design with a serene pond in the foreground, minimalist style, flat roof structures, greenery integration, soft color palette with greens and light blues, people walking, low angle shot, glass and concrete materials, hand-drawn coloring technique, subtle shading, balanced composition, depth with layering, realistic textures, proportional layout, peaceful and natural ambiance."

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    num_inference_steps=20,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")