README.md

metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - safe-for-work
  - lora
  - template:sd-lora
  - lycoris
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      A hamster wearing a tiny spacesuit in the style of a m00nl4nd1ng
      photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      A steampunk-inspired hot air balloon floating over an alien landscape in
      the style of a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: >-
      A Victorian-era robot having a tea party with stuffed animals in the style
      of a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      An astronaut skateboarding on the rings of Saturn in the style of a
      m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: >-
      A jazz band of mythical creatures performing on a floating cloud stage in
      the style of a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png
  - text: >-
      A DeLorean car with unusual attachments materializing in a medieval
      village in the style of a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_6_0.png
  - text: >-
      A futuristic city inside a giant glass dome with submarines as public
      transportation in the style of a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_0.png
  - text: >-
      A complex Rube Goldberg machine making breakfast in a Victorian kitchen in
      the style of a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: >-
      A group of friendly aliens having a picnic, with Earth visible in the
      background in the style of a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_0.png
  - text: >-
      A mechanical forest powered by a gigantic clockwork heart in the style of
      a m00nl4nd1ng photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_10_0.png

Moonlanding-Flux-ST-LoKr-36img-fal-331-full-warmup

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 wearing a tiny spacesuit in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A steampunk-inspired hot air balloon floating over an alien landscape in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A Victorian-era robot having a tea party with stuffed animals in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

An astronaut skateboarding on the rings of Saturn in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A jazz band of mythical creatures performing on a floating cloud stage in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A DeLorean car with unusual attachments materializing in a medieval village in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A futuristic city inside a giant glass dome with submarines as public transportation in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A complex Rube Goldberg machine making breakfast in a Victorian kitchen in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A group of friendly aliens having a picnic, with Earth visible in the background in the style of a m00nl4nd1ng photograph

Negative Prompt

blurry, cropped, ugly

Prompt

A mechanical forest powered by a gigantic clockwork heart in the style of a m00nl4nd1ng photograph

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: 39
• Training steps: 5000
• Learning rate: 0.0008
• 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: 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

moonlanding-36img-512

• Repeats: 2
• Total number of images: 36
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

moonlanding-36img-768

• Repeats: 2
• Total number of images: 36
• Total number of aspect buckets: 1
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

moonlanding-36img-1024

• Repeats: 0
• Total number of images: 36
• Total number of aspect buckets: 1
• Resolution: 1.048576 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 = "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")