linhqyy / jazzy-st

jazzy-st

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

The main validation prompt used during training was:

This is a digital drawing in a warm, pastel color palette, featuring a close-up view of a vintage-style coffee machine. The coffee machine is cream-colored with a golden trim and has a classic, retro design. It includes a large, circular dial on the right side, which is blue with a red pointer, indicating settings or temperature control. The coffee machine's steam wand is positioned in the center, with a dark green handle and a white steam nozzle. The steam wand is currently in use, evidenced by a small amount of coffee being extracted into a white ceramic cup placed directly below. The coffee machine's drip tray is visible beneath the cup, with a rectangular opening for the coffee to collect. The background is soft and muted, with warm tones that blend into the image, giving it a cozy and inviting atmosphere. The overall style of the drawing is reminiscent of mid-century modern design, with smooth, clean lines and a focus on warm, comforting colors.

Validation settings

• CFG: 3.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolution: 1024x1024

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: 4
• Training steps: 5000
• Learning rate: 0.0004
• Max grad norm: 2.0
• Effective batch size: 1
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_value=1.0', 'flux_lora_target=all'])
• Rescaled betas zero SNR: False
• Optimizer: adamw_bf16
• Precision: Pure BF16
• Quantised: No
• Xformers: Not used
• LoRA Rank: 64
• LoRA Alpha: None
• LoRA Dropout: 0.1
• LoRA initialisation style: default

Datasets

jazzy-512

• Repeats: 10
• Total number of images: 28
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

jazzy-1024

• 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

jazzy-512-crop

• Repeats: 10
• Total number of images: 28
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square
• Used for regularisation data: No

jazzy-1024-crop

• Repeats: 10
• Total number of images: 28
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• 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 = 'linhqyy/jazzy-st'
pipeline = DiffusionPipeline.from_pretrained(model_id), torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "This is a digital drawing in a warm, pastel color palette, featuring a close-up view of a vintage-style coffee machine. The coffee machine is cream-colored with a golden trim and has a classic, retro design. It includes a large, circular dial on the right side, which is blue with a red pointer, indicating settings or temperature control. The coffee machine's steam wand is positioned in the center, with a dark green handle and a white steam nozzle. The steam wand is currently in use, evidenced by a small amount of coffee being extracted into a white ceramic cup placed directly below. The coffee machine's drip tray is visible beneath the cup, with a rectangular opening for the coffee to collect. The background is soft and muted, with warm tones that blend into the image, giving it a cozy and inviting atmosphere. The overall style of the drawing is reminiscent of mid-century modern design, with smooth, clean lines and a focus on warm, comforting colors."


## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it 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(1641421826),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")