natural-lora-rtx3090

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

The main validation prompt used during training was:

Dense forest, ancient tree, wooden bridge, moss-covered, flowing stream, mystical atmosphere, high resolution, balanced composition, green foliage, misty background, realistic photography, soft natural light, lush greenery, nature scenery, serene, tranquil mood, detailed texture, vibrant greens, forest pathway, overgrown.

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
Dense forest, ancient tree, wooden bridge, moss-covered, flowing stream, mystical atmosphere, high resolution, balanced composition, green foliage, misty background, realistic photography, soft natural light, lush greenery, nature scenery, serene, tranquil mood, detailed texture, vibrant greens, forest pathway, overgrown.

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: 4
Training steps: 10000
Learning rate: 0.0001
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: adamw_bf16
Precision: bf16
Quantised: Yes: fp8-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

natural-booru-caption-flux

Repeats: 0
Total number of images: 1089
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: center
Crop aspect: square

natural-full-caption-flux

Repeats: 0
Total number of images: 1046
Total number of aspect buckets: 1
Resolution: 1.048576 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 = "Dense forest, ancient tree, wooden bridge, moss-covered, flowing stream, mystical atmosphere, high resolution, balanced composition, green foliage, misty background, realistic photography, soft natural light, lush greenery, nature scenery, serene, tranquil mood, detailed texture, vibrant greens, forest pathway, overgrown."

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")

datnt114
/

natural-lora-rtx3090