--- license: other base_model: "black-forest-labs/FLUX.1-dev" tags: - flux - flux-diffusers - text-to-image - diffusers - simpletuner - not-for-all-audiences - 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 c4ss4tt oil painting, A woman in a purple patterned garment holds an unclothed baby who rests against her shoulder, their arm draped over it. The background is rendered in soft, muted green tones with visible oil strokes.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_1_0.png - text: 'In the style of a c4ss4tt oil painting, A child stands wearing a red velvet outfit with white lace cuffs and a large straw hat with a black ribbon band. Their light-colored hair shows beneath the hat, and their arms are crossed at the waist against a plain, muted background.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_2_0.png - text: 'In the style of a c4ss4tt oil painting, A woman with dark hair wears a blue dress with patterned details, sitting against a green background. A child with curly blonde hair in white leans close as they examine something in the woman''s hands.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_3_0.png - text: 'In the style of a c4ss4tt oil painting, A woman in soft colors holds her baby close.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_4_0.png - text: 'In the style of a c4ss4tt oil painting, A child in a blue hat stands by a window.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_5_0.png - text: 'In the style of a c4ss4tt oil painting, Two figures lean together, loosely rendered.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_6_0.png - text: 'In the style of a c4ss4tt oil painting, A mother in casual clothes checks her phone while her baby sleeps against her shoulder, the screen''s glow creating soft highlights.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_7_0.png - text: 'In the style of a c4ss4tt oil painting, A woman shows her grandmother how to use a tablet, both faces illuminated by its light against a dark interior.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_8_0.png - text: 'In the style of a c4ss4tt oil painting, A bearded hipster holds his baby while building a chair.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_9_0.png - text: 'In the style of a c4ss4tt oil painting, A mother hamster grooms her baby hamster in a sunny window.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_10_0.png --- # Mary-Cassatt-Oil-FullAndCrops-Phase-2-ResumeFast-NormalSettings-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: `None` - Seed: `42` - Resolution: `1024x1024` 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: 4 - Training steps: 10000 - Learning rate: 0.0001 - Max grad norm: 0.1 - Effective batch size: 3 - Micro-batch size: 3 - Gradient accumulation steps: 1 - Number of GPUs: 1 - Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_value=1.0']) - Rescaled betas zero SNR: False - Optimizer: adamw_bf16 - Precision: Pure BF16 - Quantised: Yes: int8-quanto - Xformers: Not used - 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 ### cassatt-oil-512 - Repeats: 22 - Total number of images: 49 - Total number of aspect buckets: 7 - Resolution: 0.262144 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### cassatt-oil-768 - Repeats: 22 - Total number of images: 49 - Total number of aspect buckets: 8 - Resolution: 0.589824 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### cassatt-oil-1024 - Repeats: 10 - Total number of images: 49 - Total number of aspect buckets: 10 - Resolution: 1.048576 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### cassatt-oil-1536 - Repeats: 4 - Total number of images: 49 - Total number of aspect buckets: 6 - Resolution: 2.359296 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### cassatt-crops-512 - Repeats: 11 - Total number of images: 74 - Total number of aspect buckets: 1 - Resolution: 0.262144 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### cassatt-crops-768 - Repeats: 11 - Total number of images: 74 - Total number of aspect buckets: 14 - Resolution: 0.589824 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### cassatt-crops-1024 - Repeats: 5 - Total number of images: 74 - Total number of aspect buckets: 19 - Resolution: 1.048576 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### cassatt-crops-1536 - Repeats: 2 - Total number of images: 73 - Total number of aspect buckets: 24 - Resolution: 2.359296 megapixels - Cropped: False - Crop style: None - Crop aspect: None - 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/Mary-Cassatt-Oil-FullAndCrops-Phase-2-ResumeFast-NormalSettings-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(1641421826), width=1024, height=1024, guidance_scale=3.0, ).images[0] image.save("output.png", format="PNG") ```