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: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_1_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_2_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_3_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_4_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_5_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_6_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_7_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_8_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_9_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_10_0.png
- text: >-
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.
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_11_0.png
- text: >-
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.
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:
The text encoder was not trained. You may reuse the base model text encoder for inference.
Training settings
- Training epochs: 7
- Training steps: 8000
- 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: 9
- 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: 12
- 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")