Hugging Face's logo

adipanda
/
gojo-standard-lora-1

Text-to-Image
Diffusers
flux
flux-diffusers
simpletuner
safe-for-work
lora
template:sd-lora
standard
Model card Files Community
gojo-standard-lora-1 / README.md
adipanda's picture
adipanda
Model card auto-generated by SimpleTuner
7c1ac9e verified
preview code
|
raw
history blame contribute delete
5.01 kB
metadata
license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - safe-for-work
  - lora
  - template:sd-lora
  - standard
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      A scene from Jujutsu Kaisen. Gojo Satoru holding a sign that says 'I LOVE
      PROMPTS!', he is standing full body on a beach at sunset. He is wearing
      his signature black blindfold and a sleek black outfit. The setting sun
      casts a dynamic shadow on his face.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      A scene from Jujutsu Kaisen. Gojo Satoru jumping out of a propeller
      airplane, sky diving. He looks excited, his hair is blowing in the wind,
      and his blindfold is still on. The sky is clear and blue, there are birds
      pictured in the distance.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: >-
      A scene from Jujutsu Kaisen. Gojo Satoru spinning a basketball on his
      finger on a basketball court. He is wearing a Lakers jersey with the #12
      on it. The basketball hoop and crowd are in the background cheering him.
      He is smiling confidently.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      A scene from Jujutsu Kaisen. Gojo Satoru is wearing a suit in an office
      shaking the hand of a business woman. The woman has purple hair and is
      wearing professional attire. There is a Google logo in the background. It
      is during daytime, and the overall sentiment is one of accomplishment.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: >-
      A scene from Jujutsu Kaisen. Gojo Satoru is fighting a large brown grizzly
      bear, deep in a forest. The bear is tall and standing on two legs,
      roaring. The bear is also wearing a crown because it is the king of all
      bears. Around them are tall trees and other animals watching.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png

gojo-standard-lora-1

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

No validation prompt was used during training.

None

Validation settings

  • CFG: 3.5
  • CFG Rescale: 0.0
  • Steps: 20
  • Sampler: FlowMatchEulerDiscreteScheduler
  • Seed: 42
  • Resolution: 1024x1024
  • 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
A scene from Jujutsu Kaisen. Gojo Satoru holding a sign that says 'I LOVE PROMPTS!', he is standing full body on a beach at sunset. He is wearing his signature black blindfold and a sleek black outfit. The setting sun casts a dynamic shadow on his face.
Negative Prompt
blurry, cropped, ugly
Prompt
A scene from Jujutsu Kaisen. Gojo Satoru jumping out of a propeller airplane, sky diving. He looks excited, his hair is blowing in the wind, and his blindfold is still on. The sky is clear and blue, there are birds pictured in the distance.
Negative Prompt
blurry, cropped, ugly
Prompt
A scene from Jujutsu Kaisen. Gojo Satoru spinning a basketball on his finger on a basketball court. He is wearing a Lakers jersey with the #12 on it. The basketball hoop and crowd are in the background cheering him. He is smiling confidently.
Negative Prompt
blurry, cropped, ugly
Prompt
A scene from Jujutsu Kaisen. Gojo Satoru is wearing a suit in an office shaking the hand of a business woman. The woman has purple hair and is wearing professional attire. There is a Google logo in the background. It is during daytime, and the overall sentiment is one of accomplishment.
Negative Prompt
blurry, cropped, ugly
Prompt
A scene from Jujutsu Kaisen. Gojo Satoru is fighting a large brown grizzly bear, deep in a forest. The bear is tall and standing on two legs, roaring. The bear is also wearing a crown because it is the king of all bears. Around them are tall trees and other animals watching.
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: 166

  • Training steps: 3000

  • Learning rate: 0.0001

    • Learning rate schedule: constant
    • Warmup steps: 100

  • Max grad norm: 2.0

  • Effective batch size: 56

    • Micro-batch size: 56
    • 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: 0.0%

  • LoRA Rank: 128

  • LoRA Alpha: None

  • LoRA Dropout: 0.1

  • LoRA initialisation style: default

Datasets

gojo-512

  • Repeats: 2
  • Total number of images: 291
  • Total number of aspect buckets: 1
  • Resolution: 0.262144 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 = 'adipanda/gojo-standard-lora-1'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An astronaut is riding a horse through the jungles of Thailand."


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