tarot-flux-3

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

The main validation prompt used during training was:

digital comic book cover featuring Tarot

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolutions: 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
a beautifully crafted portrait, highlighting her natural beauty and unique features

Negative Prompt
blurry, cropped, ugly

Prompt
a powerful and striking portrait Tarot, capturing his strength and character

Negative Prompt
blurry, cropped, ugly

Prompt
a playful and spirited portrait of Tarot, capturing youthful energy and innocence

Negative Prompt
blurry, cropped, ugly

Prompt
a charming and vibrant portrait of Tarot, emphasizing her bright personality and joy

Negative Prompt
blurry, cropped, ugly

Prompt
a scary , digital comic book cover featuring Tarot, a Krampus licking Tarot's nipples with his long toungue

Negative Prompt
blurry, cropped, ugly

Prompt
digital comic book cover featuring Tarot

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: 195
Training steps: 4700
Learning rate: 0.001
Effective batch size: 2
- Micro-batch size: 2
- 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": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

Tarot

Repeats: 0
Total number of images: 23
Total number of aspect buckets: 1
Resolution: 0.147456 megapixels
Cropped: True
Crop style: center
Crop aspect: square

Tarot-multi

Repeats: 0
Total number of images: 23
Total number of aspect buckets: 1
Resolution: 1.0 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 = "digital comic book cover featuring Tarot"

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")

rohan871
/

tarot-flux-3