--- base_model: stabilityai/stable-diffusion-3.5-medium library_name: diffusers license: other instance_prompt: 'A jareklfoto picture of ' widget: [] tags: - text-to-image - diffusers-training - diffusers - lora - template:sd-lora - sd3 - sd3-diffusers --- # Dreambooth LoRA Weights for SD3.5 Medium Tuned on Jarek Lucek's Photos These are LoRA adaption weights for [stabilityai/stable-diffusion-3.5-medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium). Dreambooth training performed with [AdamLucek/jareklfoto-dreambooth](https://huggingface.co/datasets/AdamLucek/jareklfoto-dreambooth). `instance_prompt="A jareklfoto picture of "` Explicit permissions given for training from [Jarek Lucek](https://www.instagram.com/jarekl_foto/?hl=en), more information in dataset. **Example Images:** City Sidewalk With LoRA: City Sidewalk Without LoRA ## Intended uses & limitations #### Intended uses These LoRA weights are designed solely for educational and research purposes, intended to replicate the aesthetic and technique characteristic of Jarek Lucek's photography style. By using this model, you acknowledge that the generated images are simulations and do not reflect the original works directly. The images produced by this model are **NOT** authorized for commercial use. They may not be sold, licensed, or otherwise exploited for any commercial purpose without explicit permission from Jarek Lucek. Users must attribute the generated images directly to Jarek Lucek. Users are advised to ensure their use complies with applicable laws and respects the artistic rights of the original creator. By downloading or using this model, you agree to abide by these terms and accept full responsibility for the use of the generated images. #### How to use ```Python from diffusers import AutoPipelineForText2Image import torch # Load Model pipeline = AutoPipelineForText2Image.from_pretrained("stabilityai/stable-diffusion-3.5-medium", torch_dtype=torch.float16).to("cuda") # Load & Fuse LoRA pipeline.load_lora_weights("AdamLucek/sd3.5M-jareklfoto-LoRA-DreamBooth") lora_scale = 0.7 pipeline.fuse_lora(lora_scale=lora_scale) # Generate an Image prompt = "A jareklfoto picture of a city sidewalk" image = pipeline(prompt, num_inference_steps=28, guidance_scale=6).images[0] image.save("output_image.png") ``` ## Training details Trained using using [diffusers package](https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sd3.md). Training Script: ``` accelerate launch train_dreambooth_lora_sd3.py \ --pretrained_model_name_or_path=stabilityai/stable-diffusion-3.5-medium \ --dataset_name=AdamLucek/jareklfoto-dreambooth \ --output_dir=jareklfoto-sd35-lora-2 \ --mixed_precision="bf16" \ --instance_prompt="A jareklfoto picture of " \ --caption_column="text"\ --resolution=1024 \ --train_batch_size=1 \ --gradient_accumulation_steps=1 \ --learning_rate=4e-4 \ --report_to="wandb" \ --lr_scheduler="constant" \ --lr_warmup_steps=0 \ --max_train_steps=2000 \ --rank=64 \ --seed="0" \ --push_to_hub ```