simpletuner-lora-nvzhu2

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

The main validation prompt used during training was:

an elegant and timeless portrait of nvzhu2, exuding grace and sophistication

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 427
Resolution: 1024x768

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 <nvzhu2>, capturing her essence with vibrant colors and expressive features

Negative Prompt
blurry, cropped, ugly

Prompt
a high-quality, detailed photograph of <nvzhu2> as a sous-chef, immersed in the art of culinary creation

Negative Prompt
blurry, cropped, ugly

Prompt
a lifelike and intimate portrait of <nvzhu2>, showcasing her unique personality and charm

Negative Prompt
blurry, cropped, ugly

Prompt
a cinematic, visually stunning photo of <nvzhu2>, emphasizing her dramatic and captivating presence

Negative Prompt
blurry, cropped, ugly

Prompt
an elegant and timeless portrait of <nvzhu2>, exuding grace and sophistication

Negative Prompt
blurry, cropped, ugly

Prompt
a dynamic and adventurous photo of <nvzhu2>, captured in an exciting, action-filled moment

Negative Prompt
blurry, cropped, ugly

Prompt
a mysterious and enigmatic portrait of <nvzhu2>, shrouded in shadows and intrigue

Negative Prompt
blurry, cropped, ugly

Prompt
a vintage-style portrait of <nvzhu2>, evoking the charm and nostalgia of a bygone era

Negative Prompt
blurry, cropped, ugly

Prompt
an artistic and abstract representation of <nvzhu2>, blending creativity with visual storytelling

Negative Prompt
blurry, cropped, ugly

Prompt
a futuristic and cutting-edge portrayal of <nvzhu2>, set against a backdrop of advanced technology

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: 5
Training steps: 3000
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: optimi-stableadamwweight_decay=1e-3
Precision: Pure BF16
Quantised: Yes: int8-quanto
Xformers: Not used
LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 16,
    "apply_preset": {
        "target_module": [
            "FluxTransformerBlock",
            "FluxSingleTransformerBlock"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

nvzhu2-dataset-1536

Repeats: 0
Total number of images: 88
Total number of aspect buckets: 1
Resolution: 2.359296 megapixels
Cropped: False
Crop style: None
Crop aspect: None

nvzhu2-dataset-1024

Repeats: 0
Total number of images: 88
Total number of aspect buckets: 2
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

nvzhu2-dataset-512

Repeats: 0
Total number of images: 88
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

nvzhu2-dataset-1536-crop

Repeats: 0
Total number of images: 88
Total number of aspect buckets: 1
Resolution: 2.359296 megapixels
Cropped: True
Crop style: random
Crop aspect: square

nvzhu2-dataset_1024-crop

Repeats: 0
Total number of images: 88
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: random
Crop aspect: square

nvzhu2-dataset_512-crop

Repeats: 0
Total number of images: 88
Total number of aspect buckets: 1
Resolution: 0.262144 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 elegant and timeless portrait of nvzhu2, exuding grace and sophistication"

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=768,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")

frank-chieng
/

simpletuner-lora-nvzhu2