growwithdaisy/crtdt_20241205_165625_20241205_172840

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: FlowMatchEulerDiscreteScheduler
Seed: 69
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
crbrkn scene, A man in a hoodie and gloves is attempting to break into a red car using a crowbar.

Negative Prompt
blurry, cropped, ugly

Prompt
cplbrkp scene, the man and the woman are startled by the luggage hitting the pavement, outdoors, security footage

Negative Prompt
blurry, cropped, ugly

Prompt
cplbrkup scene, Two individuals one male and one female are in a modern room. The male is gesturing with his hand near his face while the female stands with her hands clasped. There's a TV mounted on the wall a table with a vase and fruits and a shelf with books and decorative items.

Negative Prompt
blurry, cropped, ugly

Prompt
cplbrkp scene, outdoors, security footage

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: 232
Training steps: 10000
Learning rate: 0.0001
- Learning rate schedule: constant
- Warmup steps: 0
Max grad norm: 2.0
Effective batch size: 16
- Micro-batch size: 2
- Gradient accumulation steps: 1
- Number of GPUs: 8
Gradient checkpointing: True
Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible'])
Optimizer: optimi-stableadamwweight_decay=1e-3
Trainable parameter precision: Pure BF16
Caption dropout probability: 5.0%

LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1,
    "linear_dim": 1000000,
    "linear_alpha": 1,
    "factor": 12,
    "init_lokr_norm": 0.001,
    "apply_preset": {
        "target_module": [
            "FluxTransformerBlock",
            "FluxSingleTransformerBlock"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 12
            },
            "FeedForward": {
                "factor": 6
            }
        }
    }
}

Datasets

crtdt_20241205_165625-512

Repeats: 0
Total number of images: ~208
Total number of aspect buckets: 5
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

crtdt_20241205_165625-768

Repeats: 0
Total number of images: ~208
Total number of aspect buckets: 7
Resolution: 0.589824 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

crtdt_20241205_165625-1024

Repeats: 0
Total number of images: ~192
Total number of aspect buckets: 7
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/crtdt_20241205_165625_20241205_172840'
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(69),
    width=1024,
    height=1024,
    guidance_scale=3.5,
).images[0]
image.save("output.png", format="PNG")

growwithdaisy
/

crtdt_20241205_165625_20241205_172840