0821flux-Your-name-lora64lora-training

0821flux-Your-name-lora64lora-training

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

The main validation prompt used during training was:

qxxy style,Your_name,best quality,This is a high-resolution anime still featuring a young male character with black hair wearing a white school uniform with a green and yellow tie. He appears startled or surprised, with his mouth slightly open and a hand to his cheek, as though he has just witnessed something unexpected. The setting seems to be a cafe with a modern, airy interior, as indicated by the wooden trusses on the ceiling and hanging industrial-style lamps. The daylight filters through the windows, creating a bright atmosphere. No other characters are visible, which places the entire focus on the young man's reaction.,1boy, necktie, male_focus, solo, school_uniform, indoors, striped_necktie, green_necktie, short_sleeves, shirt, upper_body

Validation settings

• CFG: 3.5
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolution: 1024

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

<Gallery />

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

Training settings

• Training epochs: 0
• Training steps: 600
• Learning rate: 0.0003
• 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: bf16
• Quantised: Yes: int8-quanto
• Xformers: Not used
• LoRA Rank: 64
• LoRA Alpha: None
• LoRA Dropout: 0.1
• LoRA initialisation style: default

Datasets

qxxy style

• Repeats: 10
• Total number of images: 488
• Total number of aspect buckets: 1
• Resolution: 1024 px
• 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 = 'wang1111magic/0821flux-Your-name-lora64lora-training'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "qxxy style,Your_name,best quality,This is a high-resolution anime still featuring a young male character with black hair wearing a white school uniform with a green and yellow tie. He appears startled or surprised, with his mouth slightly open and a hand to his cheek, as though he has just witnessed something unexpected. The setting seems to be a cafe with a modern, airy interior, as indicated by the wooden trusses on the ceiling and hanging industrial-style lamps. The daylight filters through the windows, creating a bright atmosphere. No other characters are visible, which places the entire focus on the young man's reaction.,1boy, necktie, male_focus, solo, school_uniform, indoors, striped_necktie, green_necktie, short_sleeves, shirt, upper_body"


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=1024,
    height=1024,
    guidance_scale=3.5,
).images[0]
image.save("output.png", format="PNG")