metadata

license: other
base_model: black-forest-labs/flux.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - image-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora
  - controlnet
  - template:sd-lora
  - standard
pipeline_tag: text-to-image
inference: true
widget:
  - text: A photo-realistic image of a cat
    parameters:
      negative_prompt: ugly, cropped, blurry, low-quality, mediocre average
    output:
      url: ./assets/image_0_0.png

flux-controlnet-lora-test

This is a ControlNet PEFT LoRA derived from black-forest-labs/flux.1-dev.

The main validation prompt used during training was:

A photo-realistic image of a cat

Validation settings

CFG: 4.0
CFG Rescale: 0.0
Steps: 16
Sampler: FlowMatchEulerDiscreteScheduler
Seed: 42
Resolution: 256x256
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
A photo-realistic image of a cat

Negative Prompt
ugly, cropped, blurry, low-quality, mediocre average

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

Training epochs: 209
Training steps: 2100
Learning rate: 0.0001
- Learning rate schedule: constant
- Warmup steps: 500
Max grad value: 2.0
Effective batch size: 3
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 3
Gradient checkpointing: True
Prediction type: flow_matching (extra parameters=['shift=3.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flux_lora_target=controlnet'])
Optimizer: adamw_bf16
Trainable parameter precision: Pure BF16
Base model precision: int8-quanto
Caption dropout probability: 0.0%
LoRA Rank: 64
LoRA Alpha: 64.0
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

antelope-data-256

Repeats: 0
Total number of images: ~30
Total number of aspect buckets: 1
Resolution: 0.065536 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 = 'bghira/flux-controlnet-lora-test'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "A photo-realistic image of a cat"


## 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
model_output = pipeline(
    prompt=prompt,
    num_inference_steps=16,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(42),
    width=256,
    height=256,
    guidance_scale=4.0,
).images[0]

model_output.save("output.png", format="PNG")