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: gh logo, on four cans, black background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: gh logo, green background, on a bottle and a can
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: gh logo, on a bottle and 4 cans, white background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: gh logo, on a bottle and two cans, red orange background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: gh cans, yellow background, brown red can, served with other drinks
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png
  - text: gh cans, white background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_6_0.png
  - text: gh cans, in a bucket of ice, white background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_0.png
  - text: gh cans, being held, out of focus background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: >-
      dct desert rally racing background, driving a Ducati bike, out of focus
      shrubbery
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_0.png
  - text: dct desert rally racing background, driving a Ducati bike, splashing water
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_10_0.png
  - text: >-
      dct desert rally racing background, driving a Ducati bike, rider in a
      white motocross outfit, dust cloud
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_11_0.png
  - text: >-
      dct desert rally racing background, driving a Ducati bike, view of a lake
      with shrubs and trees in the background, other riders and spectators
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_12_0.png
  - text: >-
      anytylrjy woman, wearing a neckless and an opaque brown dress standing on
      the red carpet, hair done up, front view
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_13_0.png
  - text: >-
      anytylrjy woman, putting on lipstick in front of a mirror, wearing a
      flowing white dress or bathrobe, looking in multiple mirrors, makeup on
      table
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_14_0.png
  - text: >-
      anytylrjy woman, holding a makeup kit, staring directly at camera, brown
      background, wearing a ring and eggshell dress
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_15_0.png
  - text: >-
      anytylrjy woman, wearing an elegant emerald green dress, wearing earrings
      and a necklace, white background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_16_0.png
  - text: mrtnprr style
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_17_0.png
  - text: mrtnprr style
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_18_0.png
  - text: mrtnprr style
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_19_0.png
  - text: mrtnprr style
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_20_0.png
  - text: a photo of a daisy
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_21_0.png

growwithdaisy/ghxdct_style_focus_20241113_125207

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

The main validation prompt used during training was:

a photo of a daisy

Validation settings

• CFG: 3.5
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 69
• 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

gh logo, on four cans, black background

Negative Prompt

blurry, cropped, ugly

Prompt

gh logo, green background, on a bottle and a can

Negative Prompt

blurry, cropped, ugly

Prompt

gh logo, on a bottle and 4 cans, white background

Negative Prompt

blurry, cropped, ugly

Prompt

gh logo, on a bottle and two cans, red orange background

Negative Prompt

blurry, cropped, ugly

Prompt

gh cans, yellow background, brown red can, served with other drinks

Negative Prompt

blurry, cropped, ugly

Prompt

gh cans, white background

Negative Prompt

blurry, cropped, ugly

Prompt

gh cans, in a bucket of ice, white background

Negative Prompt

blurry, cropped, ugly

Prompt

gh cans, being held, out of focus background

Negative Prompt

blurry, cropped, ugly

Prompt

dct desert rally racing background, driving a Ducati bike, out of focus shrubbery

Negative Prompt

blurry, cropped, ugly

Prompt

dct desert rally racing background, driving a Ducati bike, splashing water

Negative Prompt

blurry, cropped, ugly

Prompt

dct desert rally racing background, driving a Ducati bike, rider in a white motocross outfit, dust cloud

Negative Prompt

blurry, cropped, ugly

Prompt

dct desert rally racing background, driving a Ducati bike, view of a lake with shrubs and trees in the background, other riders and spectators

Negative Prompt

blurry, cropped, ugly

Prompt

anytylrjy woman, wearing a neckless and an opaque brown dress standing on the red carpet, hair done up, front view

Negative Prompt

blurry, cropped, ugly

Prompt

anytylrjy woman, putting on lipstick in front of a mirror, wearing a flowing white dress or bathrobe, looking in multiple mirrors, makeup on table

Negative Prompt

blurry, cropped, ugly

Prompt

anytylrjy woman, holding a makeup kit, staring directly at camera, brown background, wearing a ring and eggshell dress

Negative Prompt

blurry, cropped, ugly

Prompt

anytylrjy woman, wearing an elegant emerald green dress, wearing earrings and a necklace, white background

Negative Prompt

blurry, cropped, ugly

Prompt

mrtnprr style

Negative Prompt

blurry, cropped, ugly

Prompt

mrtnprr style

Negative Prompt

blurry, cropped, ugly

Prompt

mrtnprr style

Negative Prompt

blurry, cropped, ugly

Prompt

mrtnprr style

Negative Prompt

blurry, cropped, ugly

Prompt

a photo of a daisy

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: 44
• Training steps: 4000
• Learning rate: 5e-06
• Max grad norm: 2.0
• Effective batch size: 8
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • Number of GPUs: 8
• Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_value=1.0'])
• Rescaled betas zero SNR: False
• Optimizer: optimi-stableadamwweight_decay=1e-3
• Precision: Pure BF16
• Quantised: No
• Xformers: Not used
• LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1,
    "linear_dim": 1000000,
    "linear_alpha": 1,
    "factor": 16,
    "init_lokr_norm": 0.001,
    "apply_preset": {
        "target_module": [
            "FluxTransformerBlock",
            "FluxSingleTransformerBlock"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

gh_logo-512

• Repeats: 0
• Total number of images: ~32
• Total number of aspect buckets: 4
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

gh_cans-512

• Repeats: 0
• Total number of images: ~56
• Total number of aspect buckets: 6
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

gh_cans-768

• Repeats: 0
• Total number of images: ~40
• Total number of aspect buckets: 5
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

gh_cans-1024

• Repeats: 0
• Total number of images: ~16
• Total number of aspect buckets: 2
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

dct_desert_rally_racing_background-512

• Repeats: 0
• Total number of images: ~56
• Total number of aspect buckets: 5
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

dct_desert_rally_racing_background-768

• Repeats: 0
• Total number of images: ~56
• Total number of aspect buckets: 5
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

dct_desert_rally_racing_background-1024

• Repeats: 0
• Total number of images: ~48
• Total number of aspect buckets: 3
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

anytylrjy_woman-512

• Repeats: 0
• Total number of images: ~64
• Total number of aspect buckets: 7
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

anytylrjy_woman-768

• Repeats: 0
• Total number of images: ~64
• Total number of aspect buckets: 7
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

anytylrjy_woman-1024

• Repeats: 0
• Total number of images: ~72
• Total number of aspect buckets: 8
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

mrtnprr_style-512

• Repeats: 1
• Total number of images: ~48
• Total number of aspect buckets: 6
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

mrtnprr_style-768

• Repeats: 1
• Total number of images: ~40
• Total number of aspect buckets: 5
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

mrtnprr_style-1024

• Repeats: 1
• Total number of images: ~16
• Total number of aspect buckets: 2
• Resolution: 1.048576 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 = 'playerzer0x/growwithdaisy/ghxdct_style_focus_20241113_125207'
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 = "a photo of a daisy"


## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it 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=3.5,
).images[0]
image.save("output.png", format="PNG")