README.md

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
  - lycoris
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      p4t3ntm3ds, Elegant Victorian lady, Cordelia, holding a bottle of 'Dr.
      Worthington's Miracle Elixir'. She stands in an ornate parlor. Text
      proclaims the elixir's ability to cure all ailments and restore youth.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      p4t3ntm3ds, Muscular man, Reginald, flexing while surrounded by bottles of
      'Hercules Strength Tonic'. Ornate border includes before-and-after
      vignettes. Bold text promises instant muscle growth.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: >-
      p4t3ntm3ds, Professor Thaddeus demonstrating 'Cerebral Enhancement Drops'
      to attentive students. Blackboard filled with complex equations. Text
      boasts improved mental acuity and memory.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      p4t3ntm3ds, Socialite Genevieve applying 'Madame Rosaline's Beauty Cream'.
      Mirror reflects her radiant complexion. Floral border surrounds
      testimonials from satisfied customers.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: >-
      p4t3ntm3ds, The Thompson family gathered around table with 'Vitality
      Biscuits' box. Each family member exhibits a different benefit: strength,
      beauty, intelligence. Text explains unique formula.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png
  - text: >-
      p4t3ntm3ds, Futuristic robot, Model X-29, holding 'Cyber Tonic 3000' in
      art nouveau style laboratory. Text in LED display promises enhanced
      processing power and rust prevention.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_6_0.png
  - text: >-
      p4t3ntm3ds, Astronaut Zephyr planting flag advertising 'Cosmic Vigor
      Pills' on lunar surface. Earth visible in background. Text claims
      protection against space radiation and zero-gravity fatigue.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_0.png
  - text: >-
      p4t3ntm3ds, Mermaid Princess Coral applying 'Sea Goddess Beauty Cream'
      underwater. Fish swimming around ornate product name. Text promises scales
      as smooth as pearls.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: >-
      p4t3ntm3ds, Steampunk inventor Dr. Cogsworth showcasing 'Aether Energy
      Drops' amidst gears and pipes. Victorian text font explains how it powers
      both man and machine.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_0.png
  - text: >-
      p4t3ntm3ds, Caveman Grog and cavewoman Uga drinking from pond filled with
      'Prehistoric Vitality Water'. Friendly dinosaurs in background. Stone
      tablet text claims evolutionary advantages.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_10_0.png
  - text: >-
      p4t3ntm3ds, Dapper gentleman from 1890s, Phileas, and futuristic woman
      from 2090, Nova, toasting with 'Temporal Tonic'. Swirling time vortex in
      background. Text promises to cure past ailments and prevent future ones.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_11_0.png
  - text: >-
      p4t3ntm3ds, Alien being Zorblax demonstrating 'Universal Harmony Elixir'
      to crowd of various Earth animals. Flying saucers in sky. Text claims to
      bridge the gap between all species.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_12_0.png

Flux-Patent-Medicines-LoKr

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

No validation prompt was used during training.

None

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:

Prompt

unconditional (blank prompt)

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Elegant Victorian lady, Cordelia, holding a bottle of 'Dr. Worthington's Miracle Elixir'. She stands in an ornate parlor. Text proclaims the elixir's ability to cure all ailments and restore youth.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Muscular man, Reginald, flexing while surrounded by bottles of 'Hercules Strength Tonic'. Ornate border includes before-and-after vignettes. Bold text promises instant muscle growth.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Professor Thaddeus demonstrating 'Cerebral Enhancement Drops' to attentive students. Blackboard filled with complex equations. Text boasts improved mental acuity and memory.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Socialite Genevieve applying 'Madame Rosaline's Beauty Cream'. Mirror reflects her radiant complexion. Floral border surrounds testimonials from satisfied customers.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, The Thompson family gathered around table with 'Vitality Biscuits' box. Each family member exhibits a different benefit: strength, beauty, intelligence. Text explains unique formula.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Futuristic robot, Model X-29, holding 'Cyber Tonic 3000' in art nouveau style laboratory. Text in LED display promises enhanced processing power and rust prevention.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Astronaut Zephyr planting flag advertising 'Cosmic Vigor Pills' on lunar surface. Earth visible in background. Text claims protection against space radiation and zero-gravity fatigue.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Mermaid Princess Coral applying 'Sea Goddess Beauty Cream' underwater. Fish swimming around ornate product name. Text promises scales as smooth as pearls.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Steampunk inventor Dr. Cogsworth showcasing 'Aether Energy Drops' amidst gears and pipes. Victorian text font explains how it powers both man and machine.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Caveman Grog and cavewoman Uga drinking from pond filled with 'Prehistoric Vitality Water'. Friendly dinosaurs in background. Stone tablet text claims evolutionary advantages.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Dapper gentleman from 1890s, Phileas, and futuristic woman from 2090, Nova, toasting with 'Temporal Tonic'. Swirling time vortex in background. Text promises to cure past ailments and prevent future ones.

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of p4t3ntm3ds lithograph, Alien being Zorblax demonstrating 'Universal Harmony Elixir' to crowd of various Earth animals. Flying saucers in sky. Text claims to bridge the gap between all species.

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: 2200
• Learning rate: 0.0008
• Max grad norm: 2.0
• Effective batch size: 4
  • Micro-batch size: 4
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matchingNone
• Rescaled betas zero SNR: False
• Optimizer: adamw_bf16
• Precision: Pure BF16
• Quantised: Yes: int8-quanto
• Xformers: Not used
• LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 16,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

patent-meds-512

• Repeats: 17
• Total number of images: 83
• Total number of aspect buckets: 7
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

patent-meds-768

• Repeats: 17
• Total number of images: 83
• Total number of aspect buckets: 7
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

patent-meds-1024

• Repeats: 5
• Total number of images: 83
• Total number of aspect buckets: 17
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
wrapper.merge_to()

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

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=3.0,
).images[0]
image.save("output.png", format="PNG")