Hugging Face's logo

bghira
/
flux-dreambooth-lora-r16-dev

Text-to-Image
Diffusers
stable-diffusion
stable-diffusion-diffusers
simpletuner
lora
template:sd-lora
Model card Files Community
flux-dreambooth-lora-r16-dev / README.md
PseudoTerminal X
Update README.md
cfc2f0d verified
preview code
|
raw
history blame contribute delete
8.45 kB
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: >-
      a breathtaking anime-style portrait of Julia, capturing her essence with
      vibrant colors and expressive features
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      a high-quality, detailed photograph of Julia as a sous-chef, immersed in
      the art of culinary creation
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: >-
      a lifelike and intimate portrait of Julia, showcasing her unique
      personality and charm
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      a cinematic, visually stunning photo of Julia, emphasizing her dramatic
      and captivating presence
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: >-
      an elegant and timeless portrait of Julia, exuding grace and
      sophistication
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png
  - text: >-
      a dynamic and adventurous photo of Julia, captured in an exciting,
      action-filled moment
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_6_0.png
  - text: >-
      a mysterious and enigmatic portrait of Julia, shrouded in shadows and
      intrigue
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_0.png
  - text: >-
      a vintage-style portrait of Julia, evoking the charm and nostalgia of a
      bygone era
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: >-
      an artistic and abstract representation of Julia, blending creativity with
      visual storytelling
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_0.png
  - text: >-
      a futuristic and cutting-edge portrayal of Julia, set against a backdrop
      of advanced technology
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_10_0.png
  - text: >-
      a beautifully crafted portrait of a woman, highlighting her natural beauty
      and unique features
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_11_0.png
  - text: >-
      a powerful and striking portrait of a man, capturing his strength and
      character
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_12_0.png
  - text: >-
      a playful and spirited portrait of a boy, capturing youthful energy and
      innocence
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_13_0.png
  - text: >-
      a charming and vibrant portrait of a girl, emphasizing her bright
      personality and joy
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_14_0.png
  - text: >-
      a heartwarming and cohesive family portrait, showcasing the bonds and
      connections between loved ones
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_15_0.png
  - text: >-
      a charming and warm photograph of river phoenix at the beach on a sunny
      day
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_16_0.png
  - text: >-
      river phoenix sitting in a roller coaster car, looking like he is enjoying
      the day at the theme park
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_17_0.png
  - text: a photograph of a juggalo that is river phoenix
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_18_0.png
  - text: julie, in photograph style
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_19_0.png

flux-dreambooth-lora

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

Two subjects were trained in, a character named Julia (AI) and a real person named River Phoenix.

Empirically, training two subjects in simultaneously kept the model from collapsing, though they don't train evenly - River Phoenix took longer than "Julia", possibly due to the synthetic nature of the data.

The photos of "Julia" came from Flux Pro. River Phoenix images were pulled from Google Image Search, with a focus on high resolution, high quality samples.

No captions were used during training, only instance prompts julia and river phoenix.

The main validation prompt used during training was:

julie, in photograph style

Validation settings

  • CFG: 3.0
  • CFG Rescale: 0.0
  • Steps: 28
  • Sampler: None
  • Seed: 420420420
  • 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
a breathtaking anime-style portrait of Julia, capturing her essence with vibrant colors and expressive features
Negative Prompt
blurry, cropped, ugly
Prompt
a high-quality, detailed photograph of Julia as a sous-chef, immersed in the art of culinary creation
Negative Prompt
blurry, cropped, ugly
Prompt
a lifelike and intimate portrait of Julia, showcasing her unique personality and charm
Negative Prompt
blurry, cropped, ugly
Prompt
a cinematic, visually stunning photo of Julia, emphasizing her dramatic and captivating presence
Negative Prompt
blurry, cropped, ugly
Prompt
an elegant and timeless portrait of Julia, exuding grace and sophistication
Negative Prompt
blurry, cropped, ugly
Prompt
a dynamic and adventurous photo of Julia, captured in an exciting, action-filled moment
Negative Prompt
blurry, cropped, ugly
Prompt
a mysterious and enigmatic portrait of Julia, shrouded in shadows and intrigue
Negative Prompt
blurry, cropped, ugly
Prompt
a vintage-style portrait of Julia, evoking the charm and nostalgia of a bygone era
Negative Prompt
blurry, cropped, ugly
Prompt
an artistic and abstract representation of Julia, blending creativity with visual storytelling
Negative Prompt
blurry, cropped, ugly
Prompt
a futuristic and cutting-edge portrayal of Julia, set against a backdrop of advanced technology
Negative Prompt
blurry, cropped, ugly
Prompt
a beautifully crafted portrait of a woman, highlighting her natural beauty and unique features
Negative Prompt
blurry, cropped, ugly
Prompt
a powerful and striking portrait of a man, capturing his strength and character
Negative Prompt
blurry, cropped, ugly
Prompt
a playful and spirited portrait of a boy, capturing youthful energy and innocence
Negative Prompt
blurry, cropped, ugly
Prompt
a charming and vibrant portrait of a girl, emphasizing her bright personality and joy
Negative Prompt
blurry, cropped, ugly
Prompt
a heartwarming and cohesive family portrait, showcasing the bonds and connections between loved ones
Negative Prompt
blurry, cropped, ugly
Prompt
a charming and warm photograph of river phoenix at the beach on a sunny day
Negative Prompt
blurry, cropped, ugly
Prompt
river phoenix sitting in a roller coaster car, looking like he is enjoying the day at the theme park
Negative Prompt
blurry, cropped, ugly
Prompt
a photograph of a juggalo that is river phoenix
Negative Prompt
blurry, cropped, ugly
Prompt
julie, in photograph style
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: 108
  • Training steps: 2500
  • Learning rate: 0.0001
  • Effective batch size: 2
    • Micro-batch size: 1
    • Gradient accumulation steps: 2
    • Number of GPUs: 1
  • Prediction type: flow-matching
  • Rescaled betas zero SNR: False
  • Optimizer: AdamW, stochastic bf16
  • Precision: Pure BF16
  • Xformers: Not used
  • LoRA Rank: 16
  • LoRA Alpha: 16.0
  • LoRA Dropout: 0.1
  • LoRA initialisation style: default

Datasets

julia

  • Repeats: 0
  • Total number of images: 34
  • Total number of aspect buckets: 1
  • Resolution: 512 px
  • Cropped: True
  • Crop style: random
  • Crop aspect: square

riverphoenix

  • Repeats: 0
  • Total number of images: 12
  • Total number of aspect buckets: 1
  • Resolution: 512 px
  • Cropped: True
  • Crop style: random
  • Crop aspect: square

Inference 

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'ptx0/flux-dreambooth-lora-r16-dev'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "julie, in photograph style"

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=28,
    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")

SimpleTuner Config

The configuration used to train this model:

export MODEL_TYPE='lora'
export TRAINING_SEED=420420420

export CHECKPOINTING_STEPS=500
export CHECKPOINTING_LIMIT=10

export LEARNING_RATE=1e-4

export FLUX=true
export MODEL_NAME="black-forest-labs/FLUX.1-dev"

export VALIDATION_SEED=420420420
export VALIDATION_PROMPT="julie, in photograph style"
export VALIDATION_NEGATIVE_PROMPT="blurry, cropped, ugly"

# How frequently we will save and run a pipeline for validations.
export VALIDATION_STEPS=500

# Validation image settings.
export VALIDATION_GUIDANCE=3.0
export VALIDATION_GUIDANCE_REAL=3.0
export VALIDATION_NUM_INFERENCE_STEPS=28
export VALIDATION_GUIDANCE_RESCALE=0
export VALIDATION_RESOLUTION=1024x1024

export ALLOW_TF32=true
export PURE_BF16=true

export CAPTION_DROPOUT_PROBABILITY=0

export MAX_NUM_STEPS=0
export NUM_EPOCHS=1000

export OPTIMIZER="adamw_bf16"
export LR_SCHEDULE="constant"
export LR_WARMUP_STEPS=500

export TRAIN_BATCH_SIZE=1

export RESOLUTION=512
export RESOLUTION_TYPE=pixel

export GRADIENT_ACCUMULATION_STEPS=2
export MIXED_PRECISION="bf16"
export TRAINING_DYNAMO_BACKEND='inductor'

export USE_XFORMERS=false
export USE_GRADIENT_CHECKPOINTING=true
export VAE_BATCH_SIZE=8
export TRAINER_EXTRA_ARGS="--aspect_bucket_worker_count=48 --lora_rank=16 --lora_alpha=16 --max_grad_norm=1.0 --gradient_precision=fp32 --base_model_default_dtype=bf16 --lora_init_type=default --flux_lora_target=all+ffs --user_prompt_library=user_prompt_library.json  --webhook_config=webhooks.json --compress_disk_cache"

export USE_EMA=false