immos_flux

immos_flux

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

The main validation prompt used during training was:

Architectural sketch emphasizing large cuboid structures with red framing accents. The perspective view captures suspended white cubic volumes with red interior cutouts, connected by red steel frameworks. Three human figures in silhouette walk toward the foreground, where landscaping elements like bushes and pathways are visible. The sketch employs a mixture of precise line work and shading, highlighting texture and materiality.

Validation settings

• CFG: 3.0
• 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:

<Gallery />

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

• Training epochs: 7
• Training steps: 1000
• Learning rate: 0.0001
• 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: Yes: int8-quanto
• Xformers: Not used
• LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 16,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

my-dataset-1024

• Repeats: 3
• Total number of images: 35
• 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 = "Architectural sketch emphasizing large cuboid structures with red framing accents. The perspective view captures suspended white cubic volumes with red interior cutouts, connected by red steel frameworks. Three human figures in silhouette walk toward the foreground, where landscaping elements like bushes and pathways are visible. The sketch employs a mixture of precise line work and shading, highlighting texture and materiality."

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")