bghira/flux-dreambooth-lora-r16-dev

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