flux-training-losercity-next-lycoris13

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

The main validation prompt used during training was:

loona from helluva boss is eating a donut

Validation settings

CFG: 3.5
CFG Rescale: 0.0
Steps: 15
Sampler: None
Seed: 42
Resolution: 1024

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 this scene from the animated series "Helluva Boss," Loona, the wolf-like receptionist of the Immediate Murder Professionals (I.M.P), is depicted leaning against a wall outside the office. She is casually engrossed in her phone, displaying her typical aloof and detached demeanor. Loona's appearance includes her usual whitish fur, light grey hair, black-tipped ears, and red eyes, complemented by her punk-inspired attire featuring a black choker with spikes, a dark grey top, fingerless wrist-length black gloves, and black shorts.

Negative Prompt
blurry, cropped, ugly

Prompt
Loona shrugs with an exasperated expression, her red eyes wide and frustrated, as she seemingly questions or challenges something said in the I.M.P office. Still from Helluva boss. Loona's appearance includes her usual whitish fur, light grey hair, black-tipped ears, and red eyes, complemented by her punk-inspired attire featuring a black choker with spikes, a dark grey top, fingerless wrist-length black gloves, and black shorts.

Negative Prompt
blurry, cropped, ugly

Prompt
A scene from the animated series "Helluva Boss," set in the office. Loona, the wolf-like receptionist with white fur, black-tipped ears, and red eyes, is seated on a couch, facing towards the viewer. Loona's appearance is complemented by her punk-inspired attire featuring a black choker with spikes, a dark grey top, fingerless wrist-length black gloves, and black shorts. She holds a piece of paper that says,"Welcome to Losercity, jerks". In the background, the office has a striped wall pattern and visible damage on the ceiling, indicating a chaotic or rough environment. On the right side of the image, two imp characters appear to be engaged in conversation.

Negative Prompt
blurry, cropped, ugly

Prompt
Loona from Helluva Boss is dressed in an oversized taco costume, looking visibly irritated and embarrassed. Her red eyes convey her annoyance as she crosses her arms and glares to the side. Loona's appearance includes her usual whitish fur, light grey hair, black-tipped ears, and red eyes

Negative Prompt
blurry, cropped, ugly

Prompt
Loona is standing next to Blitzo (Helluva boss)

Negative Prompt
blurry, cropped, ugly

Prompt
In this "Helluva Boss" scene, Loona, the wolf-like receptionist, stands in an elevator with a tense and irritated expression, her teeth bared in a snarl. Blitzø, the red demon with distinctive black and white horns, leans close and makes an adorable look, as if asking for a favor. The ornate elevator setting hints at a tense moment, possibly involving a challenging mission or conflict within the I.M.P team.

Negative Prompt
blurry, cropped, ugly

Prompt
a 2D simple drawing of a madeleine cake, with a green cloud drawn next to it

Negative Prompt
blurry, cropped, ugly

Prompt
a 3D captivating YouTube thumbnail depicting of a full detailed,it's on a party real people like, on front there is a giant pulling a nose of a black African real like lady down to size of elephant nose,be creative and unique

Negative Prompt
blurry, cropped, ugly

Prompt
Whiskers the cat. Whiskers becomes a mentor to other animals.Impressed by Whiskers' intelligence, other animals in the neighborhood seek his guidance. Whiskers sets up a virtual learning platform using AI technology, where animals can ask questions, receive personalized lessons, and acquire knowledge in various subjects. Whiskers becomes a mentor, helping others unlock their potential.

Negative Prompt
blurry, cropped, ugly

Prompt
As the stock market fluctuates, the investor remains calm and collected at their desk, surrounded by charts and graphs. Their tailored suit and polished briefcase are a symbol of their expertise and experience in the world of finance.

Negative Prompt
blurry, cropped, ugly

Prompt
loona from helluva boss is eating a donut

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: 100
Learning rate: 1e-06
Effective batch size: 16
- Micro-batch size: 1
- Gradient accumulation steps: 16
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
Precision: Pure BF16
Quantised: Yes: fp8-quanto
Xformers: Not used
LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 1000000,
    "linear_alpha": 1,
    "factor": 10,
    "full_matrix": true,
    "apply_preset": {
        "target_module": [
            "FluxTransformerBlock",
            "FluxSingleTransformerBlock"
        ],
        "name_algo_map": {
            "transformer_blocks.[0-7].ff*": {
                "algo": "lokr",
                "factor": 4,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[0-7]*": {
                "algo": "lokr",
                "factor": 8,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[8-15].ff*": {
                "algo": "lokr",
                "factor": 6,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[8-15]*": {
                "algo": "lokr",
                "factor": 12,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[16-18].ff*": {
                "algo": "lokr",
                "factor": 12,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[16-18]*": {
                "algo": "lokr",
                "factor": 24,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[0-15].ff*": {
                "algo": "lokr",
                "factor": 8,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[0-15]*": {
                "algo": "lokr",
                "factor": 16,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[16-23].ff*": {
                "algo": "lokr",
                "factor": 6,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[16-23]*": {
                "algo": "lokr",
                "factor": 12,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[24-37].ff*": {
                "algo": "lokr",
                "factor": 4,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[24-37]*": {
                "algo": "lokr",
                "factor": 8,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            }
        },
        "use_fnmatch": true
    }
}

Datasets

default_dataset_arb

Repeats: 9999
Total number of images: 41
Total number of aspect buckets: 11
Resolution: 1.33 megapixels
Cropped: False
Crop style: None
Crop aspect: None

default_dataset_arb2

Repeats: 9999
Total number of images: 2565
Total number of aspect buckets: 1
Resolution: 1.33 megapixels
Cropped: False
Crop style: None
Crop aspect: None

default_dataset_arb3

Repeats: 9999
Total number of images: 3220
Total number of aspect buckets: 24
Resolution: 1.33 megapixels
Cropped: False
Crop style: None
Crop aspect: None

default_dataset

Repeats: 9999
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_512

Repeats: 9999
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_640

Repeats: 9999
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 0.4096 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_768

Repeats: 9999
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 0.589824 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_896

Repeats: 9999
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 0.802816 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_uncaptioned

Repeats: 9999
Total number of images: 2565
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_uncaptioned_512

Repeats: 9999
Total number of images: 2565
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_art

Repeats: 9999
Total number of images: 2482
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_art_512

Repeats: 9999
Total number of images: 3193
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_art_640

Repeats: 9999
Total number of images: 3115
Total number of aspect buckets: 1
Resolution: 0.4096 megapixels
Cropped: True
Crop style: random
Crop aspect: square

default_dataset_art_768

Repeats: 9999
Total number of images: 2989
Total number of aspect buckets: 1
Resolution: 0.589824 megapixels
Cropped: True
Crop style: random
Crop aspect: square

default_dataset_art_896

Repeats: 9999
Total number of images: 2787
Total number of aspect buckets: 1
Resolution: 0.802816 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 = "loona from helluva boss is eating a donut"

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=15,
    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=3.5,
).images[0]
image.save("output.png", format="PNG")

jimmycarter
/

flux-training-losercity-next-lycoris13