simpletuner-lokr-moonman

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

The main validation prompt used during training was:

A photo-realistic image of a moonman cat

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolutions: 512x512,1024x1024,1280x768

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
moonman riding a motorcycle to the sun

Negative Prompt
blurry, cropped, ugly

Prompt
moonman on the theatre broadway doing a musical. the banner overhead reads TED TALK by MOONMAN

Negative Prompt
blurry, cropped, ugly

Prompt
moonman the DJ is performing at a club in ibitha in the year 1944, there is old timey rave feeling

Negative Prompt
blurry, cropped, ugly

Prompt
moonman the anime character fighting with an anthropomorphic tree

Negative Prompt
blurry, cropped, ugly

Prompt
moonman a rollercoaster mechanic working hard on the underlying gears and structures of the famous rollercoaster

Negative Prompt
blurry, cropped, ugly

Prompt
moonman the musician on stage performing to a crowd of people

Negative Prompt
blurry, cropped, ugly

Prompt
A photo-realistic image of a moonman cat

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: 128
Training steps: 10000
Learning rate: 0.001
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-stableadamw
Precision: 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": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

moonman1024

Repeats: 0
Total number of images: 26
Total number of aspect buckets: 9
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

moonman512

Repeats: 0
Total number of images: 26
Total number of aspect buckets: 7
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

moonman768

Repeats: 0
Total number of images: 26
Total number of aspect buckets: 7
Resolution: 0.589824 megapixels
Cropped: False
Crop style: None
Crop aspect: None

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 = "A photo-realistic image of a moonman cat"

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=512,
    height=512,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")

RareConcepts
/

Flux.1-dev-LoKr-Moonman