Edit model card

growwithdaisy/sndyokly_concepts_lycoris_b1_optimi-stableadamw_2e-04_20241018_010403

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

The main validation prompt used during training was:

btythtthn woman wearing oklyflkxl sunglasses

Validation settings

  • CFG: 3.5
  • CFG Rescale: 0.0
  • Steps: 20
  • Sampler: None
  • Seed: 69
  • 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
btythtthn woman, Hair styled in two buns with vibrant colored strands, wearing a turquoise headband with symbols, striped white and green top, silver earrings, posing with hand on shoulder, against a pink background.
Negative Prompt
blurry, cropped, ugly
Prompt
The btythtthn woman has long, flowing hair; she's wearing a white top and a blue plaid shirt; the sunset paints the sky in hues of orange, pink, and purple; she stands with her back to the viewer, looking over a cityscape.
Negative Prompt
blurry, cropped, ugly
Prompt
btythtthn woman, Hair style: straight, clothing: black jacket, color: black, accessory: gold chain necklace, pose: close-up, environment: indoor with red lighting.
Negative Prompt
blurry, cropped, ugly
Prompt
btythtthn woman, Straight black hair, red bralette, red tights, gold bracelet, reclining on a checkered floor, against a red backdrop.
Negative Prompt
blurry, cropped, ugly
Prompt
oklyflkxl sunglasses, purple and green lenses, black background, front angle view
Negative Prompt
blurry, cropped, ugly
Prompt
oklyflkxl sunglasses, blue lenses, black background, front angle view
Negative Prompt
blurry, cropped, ugly
Prompt
oklyflkxl sunglasses, gray lenses, black background, straight front view
Negative Prompt
blurry, cropped, ugly
Prompt
oklyflkxl sunglasses, gray lenses, black background, side view
Negative Prompt
blurry, cropped, ugly
Prompt
a woman with dark skin wearing a sndylngkim veil, white dress, brown shoes, arms at her side, beige curtain, concrete floor
Negative Prompt
blurry, cropped, ugly
Prompt
a woman with dark skin wearing a sndylngkim veil, white dress, brown shoes, arms lifted sideways, veil opening, beige curtain, concrete floor
Negative Prompt
blurry, cropped, ugly
Prompt
a woman with dark skin wearing a sndylngkim veil, white dress, brown shoes, raising her arms in celebration, beige curtain, concrete floor
Negative Prompt
blurry, cropped, ugly
Prompt
a woman with dark skin wearing a sndylngkim veil, white dress, brown shoes, leaning with her hand against her face, workshop table, beige curtain, concrete floor
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngrctl bows
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngrctl bows
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngrctl bows
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngrctl bows
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngwing clips
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngwing clips
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngwing clips
Negative Prompt
blurry, cropped, ugly
Prompt
a photo of sndylngwing clips
Negative Prompt
blurry, cropped, ugly
Prompt
btythtthn woman wearing oklyflkxl sunglasses
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: 400
  • Learning rate: 0.0002
  • Max grad norm: 2.0
  • Effective batch size: 8
    • Micro-batch size: 1
    • Gradient accumulation steps: 1
    • Number of GPUs: 8
  • Prediction type: flow-matchingNone
  • Rescaled betas zero SNR: False
  • Optimizer: optimi-stableadamwweight_decay=1e-3
  • Precision: Pure BF16
  • Quantised: No
  • Xformers: Not used
  • LyCORIS Config:
{
    "algo": "lokr",
    "multiplier": 1,
    "linear_dim": 1000000,
    "linear_alpha": 1,
    "factor": 16,
    "init_lokr_norm": 0.001,
    "apply_preset": {
        "target_module": [
            "FluxTransformerBlock",
            "FluxSingleTransformerBlock"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

btythtthn_woman-512

  • Repeats: 0
  • Total number of images: ~240
  • Total number of aspect buckets: 5
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

btythtthn_woman-768

  • Repeats: 0
  • Total number of images: ~224
  • Total number of aspect buckets: 8
  • Resolution: 0.589824 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

btythtthn_woman-1024

  • Repeats: 0
  • Total number of images: ~176
  • Total number of aspect buckets: 8
  • Resolution: 1.048576 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

oklyflkxl_sunglasses-512

  • Repeats: 1
  • Total number of images: ~144
  • Total number of aspect buckets: 11
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

oklyflkxl_sunglasses-768

  • Repeats: 1
  • Total number of images: ~128
  • Total number of aspect buckets: 10
  • Resolution: 0.589824 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

oklyflkxl_sunglasses-1024

  • Repeats: 1
  • Total number of images: ~128
  • Total number of aspect buckets: 11
  • Resolution: 1.048576 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngkim_veil-512

  • Repeats: 1
  • Total number of images: ~56
  • Total number of aspect buckets: 5
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngkim_veil-768

  • Repeats: 1
  • Total number of images: ~56
  • Total number of aspect buckets: 5
  • Resolution: 0.589824 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngkim_veil-1024

  • Repeats: 1
  • Total number of images: ~48
  • Total number of aspect buckets: 5
  • Resolution: 1.048576 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngrctl_bows-512

  • Repeats: 1
  • Total number of images: ~72
  • Total number of aspect buckets: 8
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngrctl_bows-768

  • Repeats: 1
  • Total number of images: ~64
  • Total number of aspect buckets: 8
  • Resolution: 0.589824 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngrctl_bows-1024

  • Repeats: 1
  • Total number of images: ~48
  • Total number of aspect buckets: 5
  • Resolution: 1.048576 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngwing_clips-512

  • Repeats: 1
  • Total number of images: ~104
  • Total number of aspect buckets: 3
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngwing_clips-768

  • Repeats: 1
  • Total number of images: ~56
  • Total number of aspect buckets: 2
  • Resolution: 0.589824 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None

sndylngwing_clips-1024

  • Repeats: 1
  • Total number of images: ~48
  • Total number of aspect buckets: 4
  • 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 = "btythtthn woman wearing oklyflkxl sunglasses"

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=3.5,
).images[0]
image.save("output.png", format="PNG")
Downloads last month
0
Inference API
Examples

Model tree for playerzer0x/sndyokly_concepts_lycoris_b1_optimi-stableadamw_2e-04_20241018_010403

Adapter
(9722)
this model