README.md

metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - 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 drumming in the style of a r1ch5ull1v4n caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: a man playing the saxophone in the style of a r1ch5ull1v4n caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: >-
      a woman holding a sign that says 'I LOVE PROMPTS!' in the style of a
      r1ch5ull1v4n caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      a hipster with a beard, sitting on a chair in the style of a r1ch5ull1v4n
      caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: a female punk rocker guitarist in the style of a r1ch5ull1v4n caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png
  - text: >-
      a concert event with a pop star on stage in the spotlight.  There is a
      large crowd and flare from stadium lights in the style of a r1ch5ull1v4n
      caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_6_0.png
  - text: >-
      a man in the bayou playing a harmonica in the style of a r1ch5ull1v4n
      caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_0.png
  - text: LeBron James and Willie Nelson in the style of a r1ch5ull1v4n caricature
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: >-
      a pig, in a post apocalyptic world, with a shotgun, in a leather jacket,
      in a desert, with a motorcycle
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_0.png

sullivan_slowII

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 drumming in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

a man playing the saxophone in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

a woman holding a sign that says 'I LOVE PROMPTS!' in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

a hipster with a beard, sitting on a chair in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

a female punk rocker guitarist in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

a concert event with a pop star on stage in the spotlight. There is a large crowd and flare from stadium lights in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

a man in the bayou playing a harmonica in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

LeBron James and Willie Nelson in the style of a r1ch5ull1v4n caricature

Negative Prompt

blurry, cropped, ugly

Prompt

a pig, in a post apocalyptic world, with a shotgun, in a leather jacket, in a desert, with a motorcycle

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: 1
• Training steps: 400
• Learning rate: 0.0002
• Max grad norm: 0.1
• Effective batch size: 3
  • Micro-batch size: 3
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_value=1.0'])
• 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

sullivan-512

• Repeats: 11
• Total number of images: 22
• Total number of aspect buckets: 4
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

sullivan-768

• Repeats: 11
• Total number of images: 22
• Total number of aspect buckets: 1
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

sullivan-1024

• Repeats: 5
• Total number of images: 22
• Total number of aspect buckets: 7
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

sullivan-1536

• Repeats: 2
• Total number of images: 22
• Total number of aspect buckets: 5
• Resolution: 2.359296 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights


def download_adapter(repo_id: str):
    import os
    from huggingface_hub import hf_hub_download
    adapter_filename = "pytorch_lora_weights.safetensors"
    cache_dir = os.environ.get('HF_PATH', os.path.expanduser('~/.cache/huggingface/hub/models'))
    cleaned_adapter_path = repo_id.replace("/", "_").replace("\\", "_").replace(":", "_")
    path_to_adapter = os.path.join(cache_dir, cleaned_adapter_path)
    path_to_adapter_file = os.path.join(path_to_adapter, adapter_filename)
    os.makedirs(path_to_adapter, exist_ok=True)
    hf_hub_download(
        repo_id=repo_id, filename=adapter_filename, local_dir=path_to_adapter
    )

    return path_to_adapter_file
    
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_repo_id = 'johnbrennan/sullivan_slowII'
adapter_filename = 'pytorch_lora_weights.safetensors'
adapter_file_path = download_adapter(repo_id=adapter_repo_id)
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
wrapper.merge_to()

prompt = "An astronaut is riding a horse through the jungles of Thailand."


## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same during inference time.
from optimum.quanto import quantize, freeze, qint8
quantize(pipeline.transformer, weights=qint8)
freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
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")