Modelpublic

bghira/flux-sfwbooru-3.5M-lokr-attempt5b

sourceHugging Faceotherupdated 2y agoView on Hugging Face

3likes42downloads

Model Card

flux-sfwbooru-3.5M-lokr-attempt5b

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 cat

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.

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

—Training epochs: 0
—Training steps: 186000
—Learning rate: 2e-06
—Effective batch size: 3
—Micro-batch size: 1
—Gradient accumulation steps: 1
—Number of GPUs: 3
—Prediction type: flow-matching
—Rescaled betas zero SNR: False
—Optimizer: optimi-lion
—Precision: Pure BF16
—Quantised: Yes: int8-torchao
—Xformers: Not used
—LyCORIS Config:

json

{
    "algo": "lokr",
    "bypass_mode": true,
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 8,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 6
            },
            "FeedForward": {
                "factor": 4
            }
        }
    }
}

Datasets

sfwbooru

—Repeats: 0
—Total number of images: ~638952
—Total number of aspect buckets: 95
—Resolution: 1.048576 megapixels
—Cropped: False
—Crop style: None
—Crop aspect: None

sfwbooru-crop

—Repeats: 0
—Total number of images: ~560661
—Total number of aspect buckets: 1
—Resolution: 1.048576 megapixels
—Cropped: True
—Crop style: random
—Crop aspect: square

Inference

python

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 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=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")