--- license: other base_model: "black-forest-labs/FLUX.1-dev" tags: - flux - flux-diffusers - text-to-image - diffusers - simpletuner - safe-for-work - lora - template:sd-lora - lycoris inference: true widget: - text: 'unconditional (blank prompt)' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_0_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, A solitary figure in a long black coat stands at the edge of a pier, their back to the viewer. The dark water stretches out as a vast empty space below, while a pale moon hangs suspended in the grainy night sky.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_1_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, Two tall windows in a dimly lit room cast rectangles of pale light across an empty floor. A single wooden chair sits between them, its shadow elongated and distorted.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_2_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, A winding path through winter-bare trees leads to a small chapel with a pointed spire. The ground and sky merge in shades of grey, broken only by the stark silhouettes of branches.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_3_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, A hamster stands upright on its hind legs against an empty background, its shadow stretching impossibly long behind it. A single sunflower seed lies untouched before it.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_4_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, A Range Rover sits abandoned in deep snow, its angular form a dark mass against the white landscape. Long shadows from unseen trees stripe across its surface.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_5_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, A glass Coca-Cola bottle stands alone on a window sill, silhouetted against a pale sky. Its distinctive shape casts a elongated shadow across the bare wooden surface.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_6_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, A grandfather clock stands impossibly tall in an empty room, its pendulum frozen mid-swing. The room''s corners fade into deep shadow while pale light filters through unseen windows.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_7_0.png - text: 'In the style of a Leon Spilliaert luminous lithograph, An empty rocking chair moves by itself on a wooden porch, its curved runners leaving traces in thick dust. The surrounding space is rendered in grainy, textured darkness.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_8_0.png --- # LeonSpilliaert-Flux-LoKr This is a LyCORIS adapter derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev). No validation prompt was used during training. None ## Validation settings - CFG: `3.0` - CFG Rescale: `0.0` - Steps: `20` - Sampler: `FlowMatchEulerDiscreteScheduler` - Seed: `42` - Resolution: `896x1280` - Skip-layer guidance: Note: The validation settings are not necessarily the same as the [training settings](#training-settings). You can find some example images in the following gallery: The text encoder **was not** trained. You may reuse the base model text encoder for inference. ## Training settings - Training epochs: 33 - Training steps: 11000 - Learning rate: 8e-05 - Learning rate schedule: constant - Warmup steps: 100 - Max grad norm: 0.1 - Effective batch size: 3 - Micro-batch size: 3 - Gradient accumulation steps: 1 - Number of GPUs: 1 - Gradient checkpointing: True - Prediction type: flow-matching (extra parameters=['flux_schedule_auto_shift', 'shift=0.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flux_beta_schedule_alpha=8.0', 'flux_beta_schedule_beta=2.0', 'flow_matching_loss=compatible']) - Optimizer: adamw_bf16 - Trainable parameter precision: Pure BF16 - Caption dropout probability: 10.0% - SageAttention: Enabled inference ### LyCORIS Config: ```json { "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 ### leonspilliaert-512 - Repeats: 11 - Total number of images: 17 - Total number of aspect buckets: 2 - Resolution: 0.262144 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### leonspilliaert-768 - Repeats: 11 - Total number of images: 17 - Total number of aspect buckets: 4 - Resolution: 0.589824 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### leonspilliaert-1024 - Repeats: 5 - Total number of images: 17 - Total number of aspect buckets: 3 - Resolution: 1.048576 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### leonspilliaert-1536 - Repeats: 2 - Total number of images: 17 - Total number of aspect buckets: 3 - Resolution: 2.359296 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### leonspilliaert-crops-512 - Repeats: 11 - Total number of images: 17 - Total number of aspect buckets: 1 - Resolution: 0.262144 megapixels - Cropped: True - Crop style: random - Crop aspect: square - Used for regularisation data: No ### leonspilliaert-crops-1024 - Repeats: 5 - Total number of images: 17 - Total number of aspect buckets: 1 - Resolution: 1.048576 megapixels - Cropped: True - Crop style: random - Crop aspect: square - Used for regularisation data: No ## Inference ```python import torch from diffusers import DiffusionPipeline from lycoris import create_lycoris_from_weights def download_adapter(repo_id: str): import os from huggingface_hub import hf_hub_download adapter_filename = "pytorch_lora_weights.safetensors" cache_dir = os.environ.get('HF_PATH', os.path.expanduser('~/.cache/huggingface/hub/models')) cleaned_adapter_path = repo_id.replace("/", "_").replace("\\", "_").replace(":", "_") path_to_adapter = os.path.join(cache_dir, cleaned_adapter_path) path_to_adapter_file = os.path.join(path_to_adapter, adapter_filename) os.makedirs(path_to_adapter, exist_ok=True) hf_hub_download( repo_id=repo_id, filename=adapter_filename, local_dir=path_to_adapter ) return path_to_adapter_file model_id = 'black-forest-labs/FLUX.1-dev' adapter_repo_id = 'davidrd123/LeonSpilliaert-Flux-LoKr' adapter_filename = 'pytorch_lora_weights.safetensors' adapter_file_path = download_adapter(repo_id=adapter_repo_id) pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16 lora_scale = 1.0 wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer) wrapper.merge_to() prompt = "An astronaut is riding a horse through the jungles of Thailand." ## Optional: quantise the model to save on vram. ## Note: The model was quantised during training, and so it is recommended to do the same during inference time. from optimum.quanto import quantize, freeze, qint8 quantize(pipeline.transformer, weights=qint8) freeze(pipeline.transformer) pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level 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(42), width=896, height=1280, guidance_scale=3.0, ).images[0] image.save("output.png", format="PNG") ```