celso-portiolli-flux-lora-v1

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

The main validation prompt used during training was:

Photograph of Celso p0rt10ll1 posing in front of the Twin Towers in New York. Explosion in one of the towers. Taken on a 30mm film Kodak camera. Vintage.

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolutions: 1024x1024,896x1152

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
Photograph of Celso p0rt10ll1 posing in front of the Twin Towers in New York. Explosion in one of the towers. Taken on a 30mm film Kodak camera. Vintage.

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: 181
Training steps: 1911
Learning rate: 0.0002
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_bf16
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

p0rt10ll1

Repeats: 0
Total number of images: 21
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: center
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 = "Photograph of Celso p0rt10ll1 posing in front of the Twin Towers in New York. Explosion in one of the towers. Taken on a 30mm film Kodak camera. Vintage."

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")