Hugging Face's logo

mipat12
/
davinci-phase1-3e-4-ss3.0-wcrops

Text-to-Image
Diffusers
Safetensors
flux
flux-diffusers
simpletuner
Not-For-All-Audiences
lora
template:sd-lora
lycoris
Model card Files Community
davinci-phase1-3e-4-ss3.0-wcrops / README.md
mipat12's picture
mipat12
Model card auto-generated by SimpleTuner
7c68d78 verified
preview code
|
raw
history blame contribute delete
7.72 kB
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 hipster man with a beard, building a chair in the style of a d4v1nc1
      sketch.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: a hamster in the style of a d4v1nc1 sketch.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: a range rover on the beach in the style of a d4v1nc1 sketch.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: a Coca-Cola can product shot in the style of a d4v1nc1 sketch.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: a man holding a sign that says, 'this is a sign
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_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_6_0.png
  - text: >-
      woman holding a sign that says 'I LOVE PROMPTS!' in the style of a d4v1nc1
      sketch
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_0.png
  - text: a man operating a trebuchet in the style of a d4v1nc1 sketch
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: a screw system in the style of a d4v1nc1 sketch
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_0.png
  - text: Catapult trebuchet crossbow in the style of a d4v1nc1 sketch
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_10_0.png

davinci-phase1-3e-4-ss3.0-wcrops

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

No validation prompt was used during training.

None

Validation settings

  • CFG: 2.5
  • CFG Rescale: 0.0
  • Steps: 20
  • Sampler: FlowMatchEulerDiscreteScheduler
  • Seed: 42
  • Resolution: 1024x1024
  • Skip-layer guidance:

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 hipster man with a beard, building a chair in the style of a d4v1nc1 sketch.
Negative Prompt
blurry, cropped, ugly
Prompt
a hamster in the style of a d4v1nc1 sketch.
Negative Prompt
blurry, cropped, ugly
Prompt
a range rover on the beach in the style of a d4v1nc1 sketch.
Negative Prompt
blurry, cropped, ugly
Prompt
a Coca-Cola can product shot in the style of a d4v1nc1 sketch.
Negative Prompt
blurry, cropped, ugly
Prompt
a man holding a sign that says, 'this is a sign
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
Prompt
woman holding a sign that says 'I LOVE PROMPTS!' in the style of a d4v1nc1 sketch
Negative Prompt
blurry, cropped, ugly
Prompt
a man operating a trebuchet in the style of a d4v1nc1 sketch
Negative Prompt
blurry, cropped, ugly
Prompt
a screw system in the style of a d4v1nc1 sketch
Negative Prompt
blurry, cropped, ugly
Prompt
Catapult trebuchet crossbow in the style of a d4v1nc1 sketch
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: 5000
  • Learning rate: 0.0003
    • Learning rate schedule: polynomial
    • Warmup steps: 100
  • Max grad norm: 0.1
  • Effective batch size: 3
    • Micro-batch size: 3
    • Gradient accumulation steps: 1
    • Number of GPUs: 1
  • Gradient checkpointing: True
  • Prediction type: flow-matching (extra parameters=['shift=3.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible'])
  • Optimizer: adamw_bf16
  • Trainable parameter precision: Pure BF16
  • Caption dropout probability: 10.0%

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

davinci-512

  • Repeats: 11
  • Total number of images: 67
  • Total number of aspect buckets: 7
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None
  • Used for regularisation data: No

davinci-768

  • Repeats: 8
  • Total number of images: 67
  • Total number of aspect buckets: 12
  • Resolution: 0.589824 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None
  • Used for regularisation data: No

davinci-1024

  • Repeats: 5
  • Total number of images: 67
  • Total number of aspect buckets: 10
  • Resolution: 1.048576 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None
  • Used for regularisation data: No

davinci-1536

  • Repeats: 2
  • Total number of images: 67
  • Total number of aspect buckets: 21
  • Resolution: 2.359296 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None
  • Used for regularisation data: No

davinci-crops-512

  • Repeats: 8
  • Total number of images: 67
  • Total number of aspect buckets: 1
  • Resolution: 0.262144 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: square
  • Used for regularisation data: No

davinci-1024-crop

  • Repeats: 5
  • Total number of images: 67
  • Total number of aspect buckets: 1
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: square
  • 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 = 'mipat12/davinci-phase1-3e-4-ss3.0-wcrops'
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(42),
    width=1024,
    height=1024,
    guidance_scale=2.5,
).images[0]
image.save("output.png", format="PNG")

Exponential Moving Average (EMA)

SimpleTuner generates a safetensors variant of the EMA weights and a pt file.

The safetensors file is intended to be used for inference, and the pt file is for continuing finetuning.

The EMA model may provide a more well-rounded result, but typically will feel undertrained compared to the full model as it is a running decayed average of the model weights.