metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - 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: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_1.png
  - text: a photo of cheech marin
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: a photo of cheech marin
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_1.png
  - text: a photo of tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: a photo of tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_1.png
  - text: a photo with tommy chong sitting to the left of cheech marin
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_6_0.png
  - text: a photo with tommy chong sitting to the left of cheech marin
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_7_1.png
  - text: a photo with cheech marin sitting to the right of tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_8_0.png
  - text: a photo with cheech marin sitting to the right of tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_9_1.png
  - text: cheech and chong together in a photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_10_0.png
  - text: cheech and chong together in a photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_11_1.png
  - text: young cheech and chong in a black and white photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_12_0.png
  - text: young cheech and chong in a black and white photograph
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_13_1.png
  - text: elderly cheech and chong in an interview on the BBC
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_14_0.png
  - text: elderly cheech and chong in an interview on the BBC
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_15_1.png
  - text: old tommy chong on a sitcom in the 1990s
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_16_0.png
  - text: old tommy chong on a sitcom in the 1990s
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_17_1.png
  - text: anime cheech marin
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_18_0.png
  - text: anime cheech marin
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_19_1.png
  - text: anime tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_20_0.png
  - text: anime tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_21_1.png
  - text: A photo-realistic image of a tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_22_0.png
  - text: A photo-realistic image of a tommy chong
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_23_1.png

Flux.1-dev-LoKr-test1.4-nomask

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

The main validation prompt used during training was:

A photo-realistic image of a tommy chong

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolutions: 1024x1024,1280x768

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 photo of cheech marin

Negative Prompt
blurry, cropped, ugly

Prompt
a photo of tommy chong

Negative Prompt
blurry, cropped, ugly

Prompt
a photo with tommy chong sitting to the left of cheech marin

Negative Prompt
blurry, cropped, ugly

Prompt
a photo with cheech marin sitting to the right of tommy chong

Negative Prompt
blurry, cropped, ugly

Prompt
cheech and chong together in a photograph

Negative Prompt
blurry, cropped, ugly

Prompt
young cheech and chong in a black and white photograph

Negative Prompt
blurry, cropped, ugly

Prompt
elderly cheech and chong in an interview on the BBC

Negative Prompt
blurry, cropped, ugly

Prompt
old tommy chong on a sitcom in the 1990s

Negative Prompt
blurry, cropped, ugly

Prompt
anime cheech marin

Negative Prompt
blurry, cropped, ugly

Prompt
anime tommy chong

Negative Prompt
blurry, cropped, ugly

Prompt
A photo-realistic image of a tommy chong

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: 0
Training steps: 5400
Learning rate: 0.001
Effective batch size: 6
- Micro-batch size: 2
- Gradient accumulation steps: 1
- Number of GPUs: 3
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: optimi-stableadamwweight_decay=1e-3
Precision: Pure BF16
Quantised: Yes: int8-quanto
Xformers: Not used
LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 12,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 12
            },
            "FeedForward": {
                "factor": 6
            }
        }
    }
}

Datasets

cheechandchong-512

Repeats: 500
Total number of images: ~24
Total number of aspect buckets: 5
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

cheechandchong-1024

Repeats: 500
Total number of images: ~30
Total number of aspect buckets: 8
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

cheechandchong-512-crop

Repeats: 500
Total number of images: ~18
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: random
Crop aspect: square

cheechandchong-1024-crop

Repeats: 500
Total number of images: ~18
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: random
Crop aspect: square

regularisation-512

Repeats: 0
Total number of images: ~5886
Total number of aspect buckets: 8
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

regularisation-1024

Repeats: 0
Total number of images: ~5892
Total number of aspect buckets: 17
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

regularisation-512-crop

Repeats: 0
Total number of images: ~5874
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: random
Crop aspect: square

regularisation-1024-crop

Repeats: 0
Total number of images: ~5874
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: random
Crop aspect: square

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 = "A photo-realistic image of a tommy chong"

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")