metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - safe-for-work
  - lora
  - template:sd-lora
  - lycoris
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      an architectural sketch of a modern architecture, concrete, two stories,
      gray, windows, urban landscape, cultural building, side view, geometric
      shape, clean lines, flat roof, minimalistic design, public space, large
      mass, dominant volume, no visible vegetation, straight edges, sleek facade
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

arch_sktechs_flux_lora_v1

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

The main validation prompt used during training was:

an architectural sketch of a modern architecture, concrete, two stories, gray, windows, urban landscape, cultural building, side view, geometric shape, clean lines, flat roof, minimalistic design, public space, large mass, dominant volume, no visible vegetation, straight edges, sleek facade

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
an architectural sketch of a modern architecture, concrete, two stories, gray, windows, urban landscape, cultural building, side view, geometric shape, clean lines, flat roof, minimalistic design, public space, large mass, dominant volume, no visible vegetation, straight edges, sleek facade

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: 0
Training steps: 5000
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: Pure BF16
Quantised: No
Xformers: Not used
LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 15000,
    "linear_alpha": 2,
    "factor": 4,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 4
            },
            "FeedForward": {
                "factor": 4
            }
        }
    }
}

Datasets

img-512

Repeats: 10
Total number of images: 114
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

img-1024

Repeats: 10
Total number of images: 114
Total number of aspect buckets: 14
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

img-512-crop

Repeats: 10
Total number of images: 114
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: random
Crop aspect: square

img-1024-crop

Repeats: 10
Total number of images: 114
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: random
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 = "an architectural sketch of a modern architecture, concrete, two stories, gray, windows, urban landscape, cultural building, side view, geometric shape, clean lines, flat roof, minimalistic design, public space, large mass, dominant volume, no visible vegetation, straight edges, sleek facade"

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")