metadata

license: creativeml-openrail-m
base_model: black-forest-labs/FLUX.1-dev
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - lora
  - template:sd-lora
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly,fat
    output:
      url: ./assets/image_0_0.png
  - text: a portrait of hvvshim man on the moon
    parameters:
      negative_prompt: blurry, cropped, ugly,fat
    output:
      url: ./assets/image_1_0.png

hvvshimFluxV1

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

The main validation prompt used during training was:

a portrait of hvvshim man on the moon

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:

Prompt
unconditional (blank prompt)

Negative Prompt
blurry, cropped, ugly,fat

Prompt
a portrait of hvvshim man on the moon

Negative Prompt
blurry, cropped, ugly,fat

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

Training settings

Training epochs: 4
Training steps: 1900
Learning rate: 0.0001
Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
Prediction type: epsilon
Rescaled betas zero SNR: False
Optimizer: AdamW, stochastic bf16
Precision: Pure BF16
Xformers: Not used
LoRA Rank: 32
LoRA Alpha: 32.0
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

hvvshim

Repeats: 30
Total number of images: 15
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
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 = 'hvvshimFluxV1'
pipeline = DiffusionPipeline.from_pretrained(model_id)\pipeline.load_lora_weights(adapter_id)

prompt = "a portrait of hvvshim man on the moon"
negative_prompt = "blurry, cropped, ugly,fat"

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt='blurry, cropped, ugly,fat',
    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=1152,
    height=768,
    guidance_scale=3.5,
    guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")