flux-LoRA-r16-SOAP-4e-4-bs4
This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.
The main validation prompt used during training was:
tommy chong sitting to the left of cheech marin
Validation settings
- CFG:
3.0
- CFG Rescale:
0.0
- Steps:
20
- Sampler:
None
- Seed:
42
- Resolution:
512x512
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: 12
- Training steps: 1000
- Learning rate: 0.0008
- Effective batch size: 4
- Micro-batch size: 4
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Prediction type: flow-matching
- Rescaled betas zero SNR: False
- Optimizer: soap
- Precision: Pure BF16
- Quantised: Yes: int8-quanto
- Xformers: Not used
- LoRA Rank: 16
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
Datasets
cheechandchong-512
- Repeats: 10
- Total number of images: 17
- Total number of aspect buckets: 3
- Resolution: 0.262144 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
Inference
import torch
from diffusers import DiffusionPipeline
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'bghira/flux-LoRA-r16-SOAP-4e-4-bs4'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)
prompt = "tommy chong sitting to the left of cheech marin"
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=20,
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
width=512,
height=512,
guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")