metadata
license: other
base_model: black-forest-labs/FLUX.2-dev
tags:
- flux2
- flux2-diffusers
- text-to-image
- image-to-image
- diffusers
- simpletuner
- not-for-all-audiences
- lora
- template:sd-lora
- lycoris
pipeline_tag: text-to-image
inference: true
widget:
- text: unconditional (blank prompt)
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_0_0.png
simpletuner
This is a LyCORIS adapter derived from black-forest-labs/FLUX.2-dev.
No validation prompt was used during training.
None
Validation settings
- CFG:
7.5 - CFG Rescale:
0.0 - Steps:
30 - Sampler:
FlowMatchEulerDiscreteScheduler - Seed:
None - Resolution:
256
Note: The validation settings are not necessarily the same as the training settings.
You can find some example images in the following gallery:
- Prompt
- DLAY man in a professional studio portrait with soft lighting, high quality photography, sharp focus
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- DLAY man standing outdoors in natural sunlight, casual pose, candid photography style
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- DLAY man in a formal business suit, professional headshot, corporate photography
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- DLAY man in an artistic portrait with dramatic lighting and shadows, fine art photography
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- DLAY man in a cinematic composition, film grain, moody atmosphere, dramatic lighting
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- DLAY man in dynamic action pose, sports photography style, sharp motion capture
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- DLAY man walking through a busy city street, urban photography, street style
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- close up portrait of DLAY man, detailed face, professional lighting, 85mm lens
- 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: 0
- Training steps: 5
- Learning rate: 1.0
- Learning rate schedule: constant
- Warmup steps: 0
- Max grad value: 2.0
- Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Gradient checkpointing: False
- Prediction type: flow_matching[]
- Optimizer: prodigy (config=d_coef=2.0,weight_decay=0.01,use_bias_correction=False,schedulefree_c=75,use_orthograd=True)
- Trainable parameter precision: Pure BF16
- Base model precision:
no_change - Caption dropout probability: 0.1%
LyCORIS Config:
{
"algo": "lokr",
"multiplier": 1.0,
"factor": 12,
"linear_dim": 100000,
"linear_alpha": 1,
"conv_dim": 0,
"conv_alpha": 0,
"dora_wd": true,
"apply_preset": {
"target_module": [
"Flux2TransformerBlock",
"Flux2SingleTransformerBlock"
]
}
}
Datasets
dlay-subject-data
- Repeats: 10
- Total number of images: 269
- Total number of aspect buckets: 1
- 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.2-dev'
adapter_repo_id = 'simpletuner'
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."
negative_prompt = 'blurry, cropped, ugly'
## 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
model_output = pipeline(
prompt=prompt,
negative_prompt=negative_prompt,
num_inference_steps=30,
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
width=256,
height=256,
guidance_scale=7.5,
).images[0]
model_output.save("output.png", format="PNG")