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: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_1.png
  - text: a photo of ohwx car parking on the moon
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: a photo of ohwx car parking on the moon
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_1.png

ohwx_mo

This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.

The main validation prompt used during training was:

a photo of ohwx car parking on the moon

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 25
Sampler: None
Seed: 42
Resolutions: 1024x1024,832x1216

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
a photo of ohwx car parking on the moon

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: 120
Training steps: 3000
Learning rate: 0.0001
Effective batch size: 4
- Micro-batch size: 2
- Gradient accumulation steps: 2
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
Precision: bf16
Quantised: No
Xformers: Not used
LoRA Rank: 64
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

ohwx

Repeats: 0
Total number of images: 51
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'royi1/ohwx_mo'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "a photo of ohwx car parking on the moon"

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=25,
    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")