The main validation prompt used during training was:
TIGER_THERMOS_BOTTLE. A photo-realistic image of a gray thermos bottle on a while tabletop with mountains in the background. There is a black "TIGER" logo at the bottom of the grey thermos bottle
Validation settings
CFG: 3.5
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: 15
Training steps: 1000
Learning rate: 0.00013
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: adamw_bf16
Precision: Pure BF16
Quantised: No
Xformers: Not used
LoRA Rank: 16
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default
Datasets
default_dataset
Repeats: 10
Total number of images: 12
Total number of aspect buckets: 1
Resolution: 0.147456 megapixels
Cropped: True
Crop style: center
Crop aspect: square
Inference
import torch
from diffusers import DiffusionPipeline
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'elasticBottle/tiger-thermos-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)
prompt = "TIGER_THERMOS_BOTTLE. A photo-realistic image of a gray thermos bottle on a while tabletop with mountains in the background. There is a black "TIGER" logo at the bottom of the grey thermos bottle"
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=3.5,
).images[0]
image.save("output.png", format="PNG")