metadata

license: creativeml-openrail-m
base_model: black-forest-labs/FLUX.1-dev
tags:
  - stable-diffusion
  - stable-diffusion-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: gorkem holding a sign that says 'I LOVE FAL!'
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      gorkem with red hair, playing chess at the park, bomb going off in the
      background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: a gorkem holding a coffee cup, in a beanie, sitting at a cafe
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      gorkem showing off his cool new t shirt at the beach, a shark is jumping
      out of the water in the background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: a bear building a log cabin in the snow covered mountains
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png
  - text: >-
      woman playing the guitar, on stage, singing a song, laser lights, punk
      rocker
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_6_0.png
  - text: hipster man with a beard, building a chair, in a wood shop
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_0.png
  - text: >-
      photo of gorkem, white background, medium shot, modeling clothing, studio
      lighting, white backdrop
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: >-
      gorkem with red hair, playing chess at the park, bomb going off in the
      background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_0.png

dev-512

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

The main validation prompt used during training was:

gorkem with red hair, playing chess at the park, bomb going off in the background

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
gorkem holding a sign that says 'I LOVE FAL!'

Negative Prompt
blurry, cropped, ugly

Prompt
gorkem with red hair, playing chess at the park, bomb going off in the background

Negative Prompt
blurry, cropped, ugly

Prompt
a gorkem holding a coffee cup, in a beanie, sitting at a cafe

Negative Prompt
blurry, cropped, ugly

Prompt
gorkem showing off his cool new t shirt at the beach, a shark is jumping out of the water in the background

Negative Prompt
blurry, cropped, ugly

Prompt
a bear building a log cabin in the snow covered mountains

Negative Prompt
blurry, cropped, ugly

Prompt
woman playing the guitar, on stage, singing a song, laser lights, punk rocker

Negative Prompt
blurry, cropped, ugly

Prompt
hipster man with a beard, building a chair, in a wood shop

Negative Prompt
blurry, cropped, ugly

Prompt
photo of gorkem, white background, medium shot, modeling clothing, studio lighting, white backdrop

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: 142
Training steps: 1000
Learning rate: 0.0004
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
LoRA Rank: 16
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

dreambooth-subject

Repeats: 0
Total number of images: 7
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'Warlord-K/dev-512'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "gorkem with red hair, playing chess at the park, bomb going off in the background"


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")