maver1chh/jazzy3112

This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.

The main validation prompt used during training was:

An illustration of the beach in Malibu, California with palm trees and ocean view during sunset. A classic car is parked on an empty street next to two palm trees near a stop sign. There is a yellow line drawn across the road leading towards the beach. The sky casts long shadows over the scene, creating a warm glow that highlights the serene beauty of the landscape, illustration in classic vibes.

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: FlowMatchEulerDiscreteScheduler
Seed: 42
Resolution: 1080x1980
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
An illustration of the beach in Malibu, California with palm trees and ocean view during sunset. A classic car is parked on an empty street next to two palm trees near a stop sign. There is a yellow line drawn across the road leading towards the beach. The sky casts long shadows over the scene, creating a warm glow that highlights the serene beauty of the landscape, illustration in classic vibes.

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: 2
Training steps: 2000
Learning rate: 0.001
- Learning rate schedule: cosine_with_restarts
- Warmup steps: 1500
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: 10.0%
LoRA Rank: 16
LoRA Alpha: 16.0
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

jazz512_3112

Repeats: 10
Total number of images: 28
Total number of aspect buckets: 2
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

jazz768_3112

Repeats: 10
Total number of images: 28
Total number of aspect buckets: 1
Resolution: 0.589824 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

jazz1024_3112

Repeats: 10
Total number of images: 28
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 = 'maver1chh/maver1chh/jazzy3112'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An illustration of the beach in Malibu, California with palm trees and ocean view during sunset. A classic car is parked on an empty street next to two palm trees near a stop sign. There is a yellow line drawn across the road leading towards the beach. The sky casts long shadows over the scene, creating a warm glow that highlights the serene beauty of the landscape, illustration in classic vibes."


## 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=1080,
    height=1980,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")

Exponential Moving Average (EMA)

SimpleTuner generates a safetensors variant of the EMA weights and a pt file.

The safetensors file is intended to be used for inference, and the pt file is for continuing finetuning.

The EMA model may provide a more well-rounded result, but typically will feel undertrained compared to the full model as it is a running decayed average of the model weights.

maver1chh
/

jazzy3112