--- license: other base_model: "stabilityai/stable-diffusion-3.5-large" tags: - sd3 - sd3-diffusers - text-to-image - diffusers - simpletuner - safe-for-work - lora - template:sd-lora - standard inference: true widget: - text: 'unconditional (blank prompt)' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_0_0.png - text: 'A dark-element wolf in pixel art style, featuring a sleek body in deep black with dark purple tones and subtle midnight blue accents. Sharp, angular patterns resembling tendrils of darkness adorn its fur. The wolf’s glowing yellow eyes radiate a menacing and mysterious aura, and its tail is surrounded by faint mist-like effects. Small shadowy tendrils and pixelated wisps enhance its connection to the dark element. The plain white background keeps the focus on its enigmatic and powerful design.' parameters: negative_prompt: 'blurry, cropped, ugly' output: url: ./assets/image_1_0.png --- # 0206 This is a standard PEFT LoRA derived from [stabilityai/stable-diffusion-3.5-large](https://huggingface.co/stabilityai/stable-diffusion-3.5-large). The main validation prompt used during training was: ``` A dark-element wolf in pixel art style, featuring a sleek body in deep black with dark purple tones and subtle midnight blue accents. Sharp, angular patterns resembling tendrils of darkness adorn its fur. The wolf’s glowing yellow eyes radiate a menacing and mysterious aura, and its tail is surrounded by faint mist-like effects. Small shadowy tendrils and pixelated wisps enhance its connection to the dark element. The plain white background keeps the focus on its enigmatic and powerful design. ``` ## Validation settings - CFG: `5.0` - CFG Rescale: `0.0` - Steps: `20` - Sampler: `FlowMatchEulerDiscreteScheduler` - Seed: `42` - Resolution: `1024x1024` - 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: 18 - Training steps: 10000 - Learning rate: 8e-05 - Learning rate schedule: polynomial - Warmup steps: 100 - Max grad norm: 2.0 - Effective batch size: 1 - Micro-batch size: 1 - Gradient accumulation steps: 1 - Number of GPUs: 1 - Gradient checkpointing: True - Prediction type: flow-matching (extra parameters=['shift=3']) - Optimizer: adamw_bf16 - Trainable parameter precision: Pure BF16 - Caption dropout probability: 5.0% - LoRA Rank: 64 - LoRA Alpha: None - LoRA Dropout: 0.1 - LoRA initialisation style: default ## Datasets ### dataset-1024 - Repeats: 10 - Total number of images: 24 - Total number of aspect buckets: 1 - Resolution: 1.048576 megapixels - Cropped: False - Crop style: None - Crop aspect: None - Used for regularisation data: No ### dataset-crop-1024 - Repeats: 10 - Total number of images: 24 - Total number of aspect buckets: 1 - Resolution: 1.048576 megapixels - Cropped: True - Crop style: center - Crop aspect: square - Used for regularisation data: No ## Inference ```python import torch from diffusers import DiffusionPipeline model_id = 'stabilityai/stable-diffusion-3.5-large' adapter_id = 'badul13/0206' pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16 pipeline.load_lora_weights(adapter_id) prompt = "A dark-element wolf in pixel art style, featuring a sleek body in deep black with dark purple tones and subtle midnight blue accents. Sharp, angular patterns resembling tendrils of darkness adorn its fur. The wolf’s glowing yellow eyes radiate a menacing and mysterious aura, and its tail is surrounded by faint mist-like effects. Small shadowy tendrils and pixelated wisps enhance its connection to the dark element. The plain white background keeps the focus on its enigmatic and powerful design." negative_prompt = 'blurry, cropped, ugly' ## 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, 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(42), width=1024, height=1024, guidance_scale=5.0, ).images[0] image.save("output.png", format="PNG") ```