subliminal

This is a LyCORIS adapter derived from stabilityai/stable-diffusion-3.5-medium.

The main validation prompt used during training was:

ps2 graphics, fog filled space, subliminal

Validation settings

  • CFG: 5.0
  • 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:

Prompt
unconditional (blank prompt)
Negative Prompt
blurry, cropped, ugly
Prompt
ps2 graphics, fog filled space, subliminal
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: 4000
  • Learning rate: 0.0001
  • Max grad norm: 0.01
  • Effective batch size: 1
    • Micro-batch size: 1
    • Gradient accumulation steps: 1
    • Number of GPUs: 1
  • Prediction type: flow-matching
  • Rescaled betas zero SNR: False
  • Optimizer: adamw_bf16
  • Precision: Pure BF16
  • Quantised: No
  • Xformers: Not used
  • LyCORIS Config:
{
    "algo": "lora",
    "multiplier": 1.0,
    "linear_dim": 64,
    "linear_alpha": 32,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

subliminal-512

  • Repeats: 10
  • Total number of images: 55
  • Total number of aspect buckets: 1
  • Resolution: 0.262144 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None
  • Used for regularisation data: No

subliminal-1024

  • Repeats: 10
  • Total number of images: 55
  • Total number of aspect buckets: 2
  • Resolution: 1.048576 megapixels
  • Cropped: False
  • Crop style: None
  • Crop aspect: None
  • Used for regularisation data: No

subliminal-512-crop

  • Repeats: 10
  • Total number of images: 55
  • Total number of aspect buckets: 1
  • Resolution: 0.262144 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: square
  • Used for regularisation data: No

subliminal-1024-crop

  • Repeats: 10
  • Total number of images: 55
  • Total number of aspect buckets: 1
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: square
  • Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'stabilityai/stable-diffusion-3.5-medium'
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 = "ps2 graphics, fog filled space, subliminal"
negative_prompt = 'blurry, cropped, ugly'
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt=negative_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=5.0,
).images[0]
image.save("output.png", format="PNG")
Downloads last month
8
Inference Examples
Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for raaedk/subliminal

Adapter
(44)
this model