RareConcepts/Flux.1-dev-LoKr-PsychedeliaStyle

flux-lokr-psychedelic

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

The main validation prompt used during training was:

a psychedelic version of sandy shores, the instagram model hanging out on the beach

Validation settings

• CFG: 3.0
• CFG Rescale: 0.0
• Steps: 25
• 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

a silly psychedelic style desk telephone

Negative Prompt

blurry, cropped, ugly

Prompt

a psychedelic style pikachu

Negative Prompt

blurry, cropped, ugly

Prompt

psychedelic style batman toy

Negative Prompt

blurry, cropped, ugly

Prompt

an overhead shot of a race track shaped like psychedelic

Negative Prompt

blurry, cropped, ugly

Prompt

a woman is wearing a psychedelic necklace

Negative Prompt

blurry, cropped, ugly

Prompt

a book with the psychedelic character on the front cover

Negative Prompt

blurry, cropped, ugly

Prompt

psychedelic trip to the grand canyon

Negative Prompt

blurry, cropped, ugly

Prompt

a psychedelic version of sandy shores, the instagram model hanging out on the beach

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: 1
• Training steps: 1000
• Learning rate: 5e-05
• Effective batch size: 2
  • Micro-batch size: 2
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching
• Rescaled betas zero SNR: False
• Optimizer: optimi-lion
• Precision: bf16
• Quantised: Yes: int8-quanto
• Xformers: Not used
• LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 10,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 10
            },
            "FeedForward": {
                "factor": 6
            }
        }
    }
}

Datasets

psychedelic

• Repeats: 10
• Total number of images: 33
• Total number of aspect buckets: 1
• Resolution: 1024 px
• Cropped: True
• Crop style: center
• Crop aspect: square

psychedelic-512

• Repeats: 10
• Total number of images: 42
• Total number of aspect buckets: 1
• Resolution: 512 px
• Cropped: True
• Crop style: center
• 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 psychedelic version of sandy shores, the instagram model hanging out on the beach"

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=25,
    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")