--- base_model: stabilityai/stable-diffusion-xl-base-1.0 library_name: diffusers license: openrail++ tags: - text-to-image - text-to-image - diffusers-training - diffusers - lora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers - science - materiomics - bio-inspired - materials science instance_prompt: widget: [] --- # SDXL Fine-tuned with Leaf Images DreamBooth is an advanced technique designed for fine-tuning text-to-image diffusion models to generate personalized images of specific subjects. By leveraging a few reference images (around 5 or so), DreamBooth integrates unique visual features of the subject into the model's output domain. This is achieved by binding a unique identifier "\<..IDENTIFIER..\>", such as \ in this work, to the subject. An optional class-specific prior preservation loss can be used to maintain high fidelity and contextual diversity. The result is a model capable of synthesizing novel, photorealistic images of the subject in various scenes, poses, and lighting conditions, guided by text prompts. In this project, DreamBooth has been applied to render images with specific biological patterns, making it ideal for applications in materials science and engineering where accurate representation of biological material microstructures is crucial. For example, an original prompt might be: "a vase with intricate patterns, high quality." With the fine-tuned model, using the unique identifier, the prompt becomes: "a vase that resembles a \, high quality." This allows the model to generate images that specifically incorporate the desired biological pattern. ## Model description These are LoRA adaption weights for the SDXL-base-1.0 model (```stabilityai/stable-diffusion-xl-base-1.0```). ## Trigger keywords The following images were used during fine-tuning using the keyword \: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/sI_exTnLy6AtOFDX1-7eq.png) You should use \ to trigger this feature during image generation. [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/lamm-mit/SDXL-leaf-inspired/blob/main/SDXL_leaf_inspired_inference.ipynb) ## How to use Defining some helper functions: ```python from diffusers import DiffusionPipeline import torch import os from datetime import datetime from PIL import Image def generate_filename(base_name, extension=".png"): timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") return f"{base_name}_{timestamp}{extension}" def save_image(image, directory, base_name="image_grid"): filename = generate_filename(base_name) file_path = os.path.join(directory, filename) image.save(file_path) print(f"Image saved as {file_path}") def image_grid(imgs, rows, cols, save=True, save_dir='generated_images', base_name="image_grid", save_individual_files=False): if not os.path.exists(save_dir): os.makedirs(save_dir) assert len(imgs) == rows * cols w, h = imgs[0].size grid = Image.new('RGB', size=(cols * w, rows * h)) grid_w, grid_h = grid.size for i, img in enumerate(imgs): grid.paste(img, box=(i % cols * w, i // cols * h)) if save_individual_files: save_image(img, save_dir, base_name=base_name+f'_{i}-of-{len(imgs)}_') if save and save_dir: save_image(grid, save_dir, base_name) return grid ``` ### Text-to-image Model loading: ```python import torch from diffusers import DiffusionPipeline, AutoencoderKL repo_id='lamm-mit/SDXL-leaf-inspired' vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16) base = DiffusionPipeline.from_pretrained( "stabilityai/stable-diffusion-xl-base-1.0", vae=vae, torch_dtype=torch.float16, variant="fp16", use_safetensors=True ) base.load_lora_weights(repo_id) _ = base.to("cuda") refiner = DiffusionPipeline.from_pretrained( "stabilityai/stable-diffusion-xl-refiner-1.0", text_encoder_2=base.text_encoder_2, vae=base.vae, torch_dtype=torch.float16, use_safetensors=True, variant="fp16", ) refiner.to("cuda") ``` Image generation: ```python prompt = "a vase that resembles a , high quality" num_samples = 4 num_rows = 4 guidance_scale = 15 all_images = [] for _ in range(num_rows): # Define how many steps and what % of steps to be run on each experts (80/20) n_steps = 25 high_noise_frac = 0.8 # run both experts image = base( prompt=prompt, num_inference_steps=n_steps, guidance_scale=guidance_scale, denoising_end=high_noise_frac,num_images_per_prompt=num_samples, output_type="latent", ).images image = refiner( prompt=prompt, num_inference_steps=n_steps, guidance_scale=guidance_scale, denoising_start=high_noise_frac,num_images_per_prompt=num_samples, image=image, ).images all_images.extend(image) grid = image_grid(all_images, num_rows, num_samples, save_individual_files=True, ) grid ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/R7sr9kAwZjRk_80oMY54h.png) ## Fine-tuning script Download this script: [SDXL DreamBooth-LoRA_Fine-Tune.ipynb](https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/SDXL_DreamBooth_LoRA_Fine-Tune.ipynb) You need to create a local folder ```leaf_concept_dir_SDXL``` and add the leaf images (provided in this repository, see subfolder), like so: ```raw mkdir leaf_concept_dir_SDXL cd leaf_concept_dir_SDXL wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/0.jpeg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/1.jpeg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/2.jpeg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/3.jpeg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/87.jpg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/87.jpg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/88.jpg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/90.jpg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/91.jpg wget https://huggingface.co/lamm-mit/SDXL-leaf-inspired/resolve/main/leaf_concept_dir_SDXL/94.jpg cd .. ``` The code will automatically download the training script. The training script can handle custom prompts associated with each image, which are generated using BLIP. For instance, for the images used here, they are: ```raw {"file_name": "0.jpeg", "prompt": ", a close up of a green plant with a lot of small holes"} {"file_name": "1.jpeg", "prompt": ", a close up of a leaf with a small insect on it"} {"file_name": "2.jpeg", "prompt": ", a close up of a plant with a lot of green leaves"} {"file_name": "3.jpeg", "prompt": ", a close up of a leaf with a yellow substance in it"} {"file_name": "87.jpg", "prompt": ", a close up of a green plant with a yellow light"} {"file_name": "88.jpg", "prompt": ", a close up of a green plant with a white center"} {"file_name": "90.jpg", "prompt": ", arafed leaf with a white line on the center"} {"file_name": "91.jpg", "prompt": ", arafed image of a green leaf with a white spot"} {"file_name": "92.jpg", "prompt": ", a close up of a leaf with a yellow light shining through it"} {"file_name": "94.jpg", "prompt": ", arafed image of a green plant with a yellow cross"} ``` Training then proceeds as: ```python HF_username = 'lamm-mit' pretrained_model_name_or_path="stabilityai/stable-diffusion-xl-base-1.0" pretrained_vae_model_name_or_path="madebyollin/sdxl-vae-fp16-fix" instance_prompt ="" instance_data_dir = "./leaf_concept_dir_SDXL/" val_prompt = "a vase that resembles a , high quality" val_epochs = 100 instance_output_dir="leaf_LoRA_SDXL_V10" #for checkpointing ``` Dataset generatio with custom per-image captions ```python import requests from transformers import AutoProcessor, BlipForConditionalGeneration import torch import glob from PIL import Image import json device = "cuda" if torch.cuda.is_available() else "cpu" # load the processor and the captioning model blip_processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large") blip_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large",torch_dtype=torch.float16).to(device) # captioning utility def caption_images(input_image): inputs = blip_processor(images=input_image, return_tensors="pt").to(device, torch.float16) pixel_values = inputs.pixel_values generated_ids = blip_model.generate(pixel_values=pixel_values, max_length=50) generated_caption = blip_processor.batch_decode(generated_ids, skip_special_tokens=True)[0] return generated_caption caption_prefix = f"{instance_prompt}, " with open(f'{instance_data_dir}metadata.jsonl', 'w') as outfile: for img in imgs_and_paths: caption = caption_prefix + caption_images(img[1]).split("\n")[0] entry = {"file_name":img[0].split("/")[-1], "prompt": caption} json.dump(entry, outfile) outfile.write('\n') ``` This produces a JSON file in the ```instance_data_dir``` directory: ```raw {"file_name": "0.jpeg", "prompt": ", a close up of a green plant with a lot of small holes"} {"file_name": "1.jpeg", "prompt": ", a close up of a leaf with a small insect on it"} {"file_name": "2.jpeg", "prompt": ", a close up of a plant with a lot of green leaves"} {"file_name": "3.jpeg", "prompt": ", a close up of a leaf with a yellow substance in it"} {"file_name": "87.jpg", "prompt": ", a close up of a green plant with a yellow light"} {"file_name": "88.jpg", "prompt": ", a close up of a green plant with a white center"} {"file_name": "90.jpg", "prompt": ", arafed leaf with a white line on the center"} {"file_name": "91.jpg", "prompt": ", arafed image of a green leaf with a white spot"} {"file_name": "92.jpg", "prompt": ", a close up of a leaf with a yellow light shining through it"} {"file_name": "94.jpg", "prompt": ", arafed image of a green plant with a yellow cross"} ``` ```python !accelerate launch train_dreambooth_lora_sdxl.py \ --pretrained_model_name_or_path="{pretrained_model_name_or_path}" \ --pretrained_vae_model_name_or_path="{pretrained_vae_model_name_or_path}"\ --dataset_name="{instance_data_dir}" \ --output_dir="{instance_output_dir}" \ --caption_column="prompt"\ --mixed_precision="fp16" \ --instance_prompt="{instance_prompt}" \ --validation_prompt="{val_prompt}" \ --validation_epochs="{val_epochs}" \ --resolution=1024 \ --train_batch_size=1 \ --gradient_accumulation_steps=3 \ --gradient_checkpointing \ --learning_rate=1e-4 \ --snr_gamma=5.0 \ --lr_scheduler="constant" \ --lr_warmup_steps=0 \ --mixed_precision="fp16" \ --use_8bit_adam \ --max_train_steps=500 \ --checkpointing_steps=500 \ --seed="0" ``` ### With prior preservation Set `--with_prior_preservation` flag to include prior preservation. In this case you must specify `--class_data_dir` (directory with class images) and `--class_prompt` (class prompt). You should also set `--num_class_images` to specify how many class preservation images you want to use. Either place them in the directory (specified via `--class_data_dir`) or the code with auto-generate them based off the base model. You can also provide a few yourself and let the code generate the remaining ones. An example is provided below, commented out. The code that will run here will NOT use prior preservation. Some other useful parameters that can be set include: --rank: LoRA adapter rank (LoRA alpha will be set identical to rank) --use_dora: Set if you want to use DORA Type ```python train_dreambooth_lora_sdxl.py``` to get a full list of parameters ```python instance_data_dir = 'local_instance_data_dir' class_prompt = 'a prompt that describes the images in the directory local_instance_data_dir' num_class_images = 10 #how many images you want in this class !\accelerate launch train_dreambooth_lora_sdxl.py \ --pretrained_model_name_or_path="{pretrained_model_name_or_path}" \ --pretrained_vae_model_name_or_path="{pretrained_vae_model_name_or_path}"\ --dataset_name="{instance_data_dir}" \ --class_prompt="{class_prompt}" \ --num_class_images={num_class_images} \ --with_prior_preservation \ --class_data_dir="{class_data_dir}" \ --output_dir="{instance_output_dir}" \ --caption_column="prompt"\ --mixed_precision="fp16" \ --instance_prompt="{instance_prompt}" \ --validation_prompt="{val_prompt}" \ --validation_epochs={val_epochs} \ --resolution=1024 \ --train_batch_size=1 \ --gradient_accumulation_steps=4 \ --gradient_checkpointing \ --learning_rate=1e-4 \ --snr_gamma=5.0 \ --lr_scheduler="constant" \ --lr_warmup_steps=0 \ --mixed_precision="fp16" \ --use_8bit_adam \ --max_train_steps=500 \ --checkpointing_steps=500 \ --seed="0" ```