hbxartdev/kraken-flux-lora
08
kraken-flux-lora
This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.
The main validation prompt used during training was:
editorial close-up of a woman, glowing flawless skin, peach blush and gloss, nude shimmer lips, editorial studio lightValidation settings
- CFG:
3.0 - 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:
<Gallery />
The text encoder was not trained. You may reuse the base model text encoder for inference.
Training settings
- Training epochs: 15
- Training steps: 2000
- Learning rate: 0.0002
- Learning rate schedule: constant
- Warmup steps: 100
- Max grad value: 2.0
- Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Gradient checkpointing: True
- Prediction type: flowmatching (extra parameters=['shift=3', 'fluxguidancemode=constant', 'fluxguidancevalue=1.0', 'fluxlora_target=all'])
- Optimizer: adamw_bf16
- Trainable parameter precision: Pure BF16
- Base model precision:
no_change - Caption dropout probability: 0.05%
- LoRA Rank: 16
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
Datasets
default_dataset
- Repeats: 0
- Total number of images: 125
- Total number of aspect buckets: 1
- Resolution: 0.147456 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
Inference
import torch
from diffusers import DiffusionPipeline
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'hbxartdev/kraken-flux-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)
prompt = "editorial close-up of a woman, glowing flawless skin, peach blush and gloss, nude shimmer lips, editorial studio light"
## 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,
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=3.0,
).images[0]
model_output.save("output.png", format="PNG")
