debug-2024-02-12

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+datasets/

GirlsFrontline_SDXL_LoRA.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f168686ba31428c672400c5a20e07c8c8b66addf2ce85c8315407eb52316dd1a
+size 228487908

README.md

@@ -0,0 +1,128 @@
+---
+language: en
+thumbnail: ./assets/example.png
+tags:
+- text-to-image
+- diffusion models
+- LoRA fine-tuning
+- animagine-xl-3.0
+- stable_diffusion_xl
+- kohya_ss
+- waifu2x
+license: apache-2.0
+model:
+  name: SDXL-LoRA-Text2Image
+  description: A model based on SDXL with LoRA fine-tuning for Text-To-Image generation.
+  pipeline_tag: image-generation
+  repo: https://huggingface.co/TfiyuenLau/GirlsFrontline_SDXL_LoRA
+  library: huggingface
+  framework: pytorch
+  version: 1.0.0
+  pretrained_model: stable_diffusion_xl
+  base_model: animagine-xl-3.0
+  fine_tuner: kohya_ss
+  data_augmentation: waifu2x
+  task: text-to-image
+---
+
+# 基于SDXL模型LoRA微调实现Text-To-Image文生图
+
+![example](./assets/example.png)
+
+## 一、Model Library
+1. 微调数据集：[基于SDXL模型的《少女前线2：追放》LoRA微调数据集](https://www.kaggle.com/datasets/yukikonata/sdxl2lora)
+2. 预训练模型：[stable_diffusion_xl](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/stable_diffusion_xl)
+3. 底模：[animagine-xl-3.0](https://huggingface.co/cagliostrolab/animagine-xl-3.0)
+4. SDXL LoRA微调训练器：[kohya_ss](https://github.com/bmaltais/kohya_ss)
+5. 数据集画质增强：[waifu2x](https://github.com/nagadomi/waifu2x)
+
+## 二、Prompt Dict
+1. 少前2追放角色5
+* 佩里缇亚: PKPSP
+* 塞布丽娜: SPAS12
+* 托洛洛: AKAlfa
+* 桑朵莱希: G36
+* 琼玖: QBZ191
+* 维普雷: Vepr12
+* 莫辛纳甘: MosinNagant
+* 黛烟: QBZ95
+* 克罗丽科: Kroliko
+* 夏克里: XCRL
+* 奇塔: MP7
+* 寇尔芙: TaurusCurve
+* 科谢尼娅: APS
+* 纳甘: Nagant1895
+* 纳美西丝: OM50
+* 莉塔拉: GalilARM
+* 闪电: OTs14
+
+2. Pixiv画师风格
+* おにねこ（鬼猫）: Onineko26
+* 麻生: AsouAsabu
+* mignon: Mignon
+* migolu: Migolu
+
+## 三、使用方式
+1. 安装部分环境（默认已安装pytorch等必要环境）
+~~~sh
+pip install diffusers --upgrade
+pip install transformers accelerate safetensors
+~~~
+
+2. 使用Hugging Face下载并使用底模（animagine-xl-3.0）和LoRA模型
+~~~python
+import torch
+import datetime
+from PIL import Image
+import matplotlib.pyplot as plt
+from diffusers import (
+  StableDiffusionXLPipeline, 
+  EulerAncestralDiscreteScheduler,
+  AutoencoderKL
+)
+
+# LoRA Hugging Face ID
+lora_id = "TfiyuenLau/GirlsFrontline_SDXL_LoRA"
+
+# Load VAE component
+vae = AutoencoderKL.from_pretrained(
+  "madebyollin/sdxl-vae-fp16-fix", 
+  torch_dtype=torch.float16
+)
+
+# Configure the pipeline
+pipe = StableDiffusionXLPipeline.from_pretrained(
+  "cagliostrolab/animagine-xl-3.0", 
+  vae=vae,
+  torch_dtype=torch.float16, 
+  use_safetensors=True, 
+)
+pipe.load_lora_weights(lora_id)
+pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
+pipe.to('cuda')
+~~~
+
+3. 生成图像
+~~~python
+# Define Prompt
+output = "./output.png"
+prompt = "1girl, OTs14, gloves, looking at viewer, smile, food, holding, solo, closed mouth, sitting, yellow eyes, black gloves, masterpiece, best quality"
+negative_prompt = "nsfw, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name"
+
+# Generate Image
+image = pipe(
+  prompt, 
+  negative_prompt=negative_prompt, 
+  width=1024,
+  height=1024,
+  guidance_scale=7,
+  num_inference_steps=28
+).images[0]
+
+# Save & Show
+image.save(output)
+image = Image.open(output)
+plt.axis('off')
+plt.imshow(image)
+image.close()
+~~~

assets/events.out.tfevents.1707400528.autodl-container-76db429c66-9866c56d.2317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e90d8de21a92470deb6bcdb3e5c92d84eb64c1357e2417e65ebe20dc47e30f
+size 8434946

assets/events.out.tfevents.1707463908.autodl-container-76db429c66-9866c56d.1301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f83386197ebd96624993d1d09b27a18aa5ff0dfacb4937c6f8b3e3c4c2a2e62
+size 20561120