glassobject-lokr-flux
This is a LyCORIS adapter derived from black-forest-labs/FLUX.1-dev.
The main validation prompt used during training was:
a glassobject style photograph with main green and blue accents
Validation settings
- CFG:
3.0 - CFG Rescale:
0.0 - Steps:
15 - Sampler:
None - Seed:
4412 - 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:
The text encoder was not trained. You may reuse the base model text encoder for inference.
Training settings
- Training epochs: 0
- Training steps: 5200
- Learning rate: 0.0005
- Effective batch size: 2
- Micro-batch size: 2
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Prediction type: flow-matching
- Rescaled betas zero SNR: False
- Optimizer: optimi-lion
- Precision: Pure BF16
- Quantised: Yes: int8-quanto
- Xformers: Not used
- 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
glassobject-512
- Repeats: 5
- Total number of images: 894
- Total number of aspect buckets: 2
- Resolution: 0.262144 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
glassobject-1024
- Repeats: 5
- Total number of images: 894
- Total number of aspect buckets: 4
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
glassobject-512-crop
- Repeats: 5
- Total number of images: 894
- Total number of aspect buckets: 1
- Resolution: 0.262144 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
glassobject-1024-crop
- Repeats: 5
- Total number of images: 894
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
Inference
import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
wrapper.merge_to()
prompt = "a glassobject style photograph with main green and blue accents"
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
prompt=prompt,
num_inference_steps=15,
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=3.0,
).images[0]
image.save("output.png", format="PNG")