SDFT
1.0.0
SDFT是一个自我教育项目，旨在概述主要的稳定扩散微调技术。稳定的扩散实现来自拥抱面扩散器库。
概述的技术：
所有微调技术均在一个名为“ Dark Fantasy”的手工制造的玩具数据集上进行。使用稳定的扩散XL Base-1.0模型从SteStieAI中收集数据集，以使人联想到1970年代和1980年代的样式，从而生成类似深色幻想的图像。目的是说明如何在此数据集中概述所有技术。
数据集可以在datasets/目录下找到。
用洛拉微调SDXL：
accelerate launch train_lora_sdxl.py
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0
--pretrained_vae_model_name_or_path=madebyollin/sdxl-vae-fp16-fix
--allow_tf32
--mixed_precision= " fp16 "
--rank=32
--train_data_dir=datasets/dark_fantasy/
--caption_column= " text "
--dataloader_num_workers=16
--resolution=512
--use_center_crop
--use_random_flip
--train_batch_size=2
--gradient_accumulation_steps=4 --gradient_checkpointing
--max_train_steps=1500
--learning_rate=1e-04
--max_grad_norm=5
--lr_scheduler= " cosine_with_restarts "
--lr_warmup_steps=100
--output_dir=runs/lora_run/
--checkpointing_steps=100
--validation_epochs=10
--num_validation_images=4
--save_images_on_disk
--validation_prompt= " A picture of a misterious figure in cape, back view. "
--logging_dir= " logs "
--seed=1337使用LORA检查点进行推断：
accelerate launch run_lora_inference.py
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0
--pretrained_vae_model_name_or_path=madebyollin/sdxl-vae-fp16-fix
--output_dir=runs/lora_v1/
--lora_checkpoint_path=runs/lora_run/checkpoint-100/
--resolution=1024
--num_images_to_generate=5
--guidance_scale=5.0
--num_inference_steps=40
--prompt= " A picture of a misterious figure in cape, back view. "
--negative_prompt= " logo, watermark, text, blurry "
--seed=1337无洛拉 - 洛拉图像比较。使用同一潜伏期生成成对的图像。
"A picture of a heavy red Kenworth truck riding in the night across the abanoned city streets."
"A picture of a wounded orc warrior, climbing in misty mountains, front view, exhausted face, looking at the camera."
"A picture of space rocket launching, Earth on the background, candid photo."
"A picture of a supermassive black hole, devouring the galaxy, cinematic picture"
"A picture of a human woman warrior, black hair, looking at the camera, front view."
用文本反演（Ti）微调SDXL：
accelerate launch train_ti_sdxl.py
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0
--pretrained_vae_model_name_or_path=madebyollin/sdxl-vae-fp16-fix
--allow_tf32
--mixed_precision= " fp16 "
--train_data_dir=datasets/skull
--learnable_property= " style "
--placeholder_token= " <skull_lamp> "
--initializer_token= " skull "
--num_vectors=8
--resolution=1024
--repeats=1
--train_batch_size=2
--gradient_accumulation_steps=4 --gradient_checkpointing
--max_train_steps=5000
--learning_rate=3e-3
--lr_scheduler= " piecewise_constant "
--lr_warmup_steps=30
--output_dir= " runs/ti_run "
--validation_prompt= " A painting of Eiffel tower in the style of <skull_lamp> "
--num_validation_images=4
--validation_steps=100
--embeddings_save_steps=500
--save_images_on_disk
--use_random_flip
--use_center_crop
--seed=1337 使用训练有素的TI嵌入进行推断：
accelerate launch run_ti_inference.py
--pretrained_model_name_or_path=stabilityai/stable-diffusion-xl-base-1.0
--pretrained_vae_model_name_or_path=madebyollin/sdxl-vae-fp16-fix
--output_dir=runs/ti_run
--path_to_embeddings=runs/ti_run/ti-embeddings-final.safetensors
--resolution=1024
--num_images_to_generate=1
--guidance_scale=5.0
--num_inference_steps=50
--placeholder_token= " <skull_lamp> "
--prompt= " A <skull_lamp>, made of lego "
--negative_prompt= " logo, watermark, text, blurry, bad quality "
--seed=1337没有Ti -Ti图像比较。使用同一潜伏期生成成对的图像。
注意：由于培训数据集仅包含5个带有默认字幕的图像，因此结果并不令人鼓舞，但是引入更多的细粒字幕会使它变得更好。
"A <skull_lamp>, made of lego."
"A painting of Eiffel tower in the style of <skull_lamp>."
"A painting of the great pyramids in the style of <skull_lamp>."
"An oil painting of a skyscraper in the style of <skull_lamp>."
"The painting of a mug in the style of <skull_lamp>."
