sullivan_refined

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

No validation prompt was used during training.

None

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
a hamster drumming in the style of a r1ch5ull1v4n caricature

Negative Prompt
blurry, cropped, ugly

Prompt
a man playing the saxophone in the style of a r1ch5ull1v4n caricature

Negative Prompt
blurry, cropped, ugly

Prompt
a woman holding a sign that says 'I LOVE PROMPTS!' in the style of a r1ch5ull1v4n caricature

Negative Prompt
blurry, cropped, ugly

Prompt
a hipster with a beard, building a chair in the style of a r1ch5ull1v4n caricature

Negative Prompt
blurry, cropped, ugly

Prompt
a transgender guitarist in the style of a r1ch5ull1v4n caricature

Negative Prompt
blurry, cropped, ugly

Prompt
concert event, pop star in motion, crowd blurred, flare from stadium lights in the style of a r1ch5ull1v4n caricature

Negative Prompt
blurry, cropped, ugly

Prompt
Two superheroes fighting a croissant in the style of a r1ch5ull1v4n caricature

Negative Prompt
blurry, cropped, ugly

Prompt
LeBron James and Shaquille O'Neal

Negative Prompt
blurry, cropped, ugly

Prompt
a pig, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle

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: 44
Training steps: 7000
Learning rate: 0.0002
Max grad norm: 0.1
Effective batch size: 6
- Micro-batch size: 3
- Gradient accumulation steps: 2
- Number of GPUs: 1
Prediction type: flow-matching (flux parameters=['shift=3', 'flux_guidance_value=1.0'])
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
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": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

sullivan-512

Repeats: 11
Total number of images: 22
Total number of aspect buckets: 4
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

sullivan-768

Repeats: 11
Total number of images: 22
Total number of aspect buckets: 6
Resolution: 0.589824 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

sullivan-1024

Repeats: 5
Total number of images: 22
Total number of aspect buckets: 7
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

sullivan-1536

Repeats: 2
Total number of images: 22
Total number of aspect buckets: 8
Resolution: 2.359296 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

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 astronaut is riding a horse through the jungles of Thailand."

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")

johnbrennan
/

sullivan_refined