license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
- flux
- flux-diffusers
- text-to-image
- diffusers
- simpletuner
- safe-for-work
- lora
- template:sd-lora
- standard
inference: true
widget:
- text: unconditional (blank prompt)
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_0_0.png
- text: Minimalist icon, alert circle
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_1_0.png
- text: Minimalist icon, mood smile
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_2_0.png
- text: Minimalist icon, brand facebook
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_3_0.png
- text: Minimalist icon, badge hd
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_4_0.png
- text: Minimalist icon, coin off
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_5_0.png
- text: Minimalist icon, arrow up
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_6_0.png
icon-generator
This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.
The main validation prompt used during training was:
Minimalist icon, arrow up
Validation 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:
- Prompt
- unconditional (blank prompt)
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- Minimalist icon, alert circle
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- Minimalist icon, mood smile
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- Minimalist icon, brand facebook
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- Minimalist icon, badge hd
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- Minimalist icon, coin off
- Negative Prompt
- blurry, cropped, ugly
- Prompt
- Minimalist icon, arrow up
- 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: 1000
Learning rate: 8e-05
- Learning rate schedule: polynomial
- Warmup steps: 100
Max grad norm: 1.0
Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
Gradient checkpointing: True
Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible', 'flux_lora_target=all'])
Optimizer: adamw_bf16
Trainable parameter precision: Pure BF16
Caption dropout probability: 5.0%
LoRA Rank: 16
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default
Datasets
tabler-icons-1024
- Repeats: 10
- Total number of images: 4739
- 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
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'noahyoungs/icon-generator'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)
prompt = "Minimalist icon, arrow up"
## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same 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
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(42),
width=1024,
height=1024,
guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")