---

Viewer: 🖼️LoRAs Gallery

MainPage

---

Dataset:📊Dataset Collections

---

Training Configuration & Tools

1. Krea2

• Training Tools: Onetrainer
• Dataset: At least 50 images (averaging 100+)
• Tagging Style: Mixed format (Booru tags as prefixes combined with natural language)
• Training Res: 512x512
• Repeats per Image: 50+
• Training Parameters: Default settings from Onetrainer
• Showcase Image Parameters:
  • Model:
    • Dark Beast 2
    • Kreamania v6
  • LoRA Weight: 0.8 ~ 1

2. Anima

• Training Tools: Onetrainer
• Dataset: 20 ~ 100 images
• Tagging Style: Mixed format (Booru tags as prefixes combined with natural language)
• Training Res: 512x512
• Repeats per Image: 50+
• Training Parameters: Default settings from Onetrainer
• Showcase Image Parameters:
  • Model:
    • Diving Anima v40
  • LoRA Weight: 0.8 ~ 1

3. Flux 1 Dev

• Training Tools: Kohya_ss GUI / AI-Toolkit
• Dataset: 20-50 images
• Tagging Style: Early stages used Booru tags; later shifted to natural language descriptive captions
• Training Res: 512x512
• Repeats per Image: 50+
• Training Parameters: Default settings from Kohya_ss / AI-Toolkit
• Showcase Image Parameters:
  • Model:
    • RedCraft New REVE[A]L
    • UltraReal Fine-Tune
    • BEYOND REALITY 超越真实 v3
    • Flux 1 Dev
  • LoRA Weight: 0.8 ~ 1

4. SD1.5 & Pony

• Tool: Kohya Colab
• Dataset: 50-200 images
• Tagging Style: Booru tags
• Training Res: 1024x1024+
• Repeats per Image: 30 - 50
• Training Parameters: Default settings from the Colab notebook
• Showcase Image Parameters:
  • Model:
    • PONY: WAI-ANI-HENTAI-PONYXL v6
    • SD1.5: t3 sd ver3
    • SD1.5: MeichiDarkMix_Legacy
    • SD1.5: RedCraft Resolution 1.5
  • LoRA Weight: 0.8 ~ 1

---

Usage Disclaimer

1. Educational & Research Purpose Only: This repository hosts LoRA models trained on various base models, including Pony, Flux 1 Dev, Anima, Krea2, and SD1.5. All models are intended solely for academic exchange, technical testing, and personal research into image generation algorithms.
2. Prohibition of Illegal Use: Users must strictly adhere to local laws and regulations when downloading and using these models. It is strictly forbidden to use these models to infringe upon others' privacy, reputation, portrait rights, or other legitimate interests. Do not use them for creating or spreading misinformation, fraudulent activities, or any unethical purposes.
3. Takedown Notice: These models are shared for non-commercial research purposes. If you are a copyright owner or an authorized agent and believe that any content in this repository infringes upon your rights, please contact me directly. I will promptly review and remove the infringing material upon verification, without any delay.
4. Content Compliance Notice: Please be aware that certain base models (e.g., Pony) may exhibit a high degree of openness regarding specific prompts. Users are entirely responsible for filtering and auditing the compliance of the generated content.
5. Limitation of Liability: As the creator/tester of these experimental models, I take no responsibility for any direct or indirect legal liabilities, losses, or disputes arising from the use of this repository. Any image generated and its subsequent consequences are the sole responsibility of the user.

---

使用免责声明

1. 仅限教育与研究目的：本仓库托管了基于多种基础模型（包括 Pony、Flux 1 Dev、Krea2、Anima 和 SD1.5）训练的 LoRA 模型。所有模型仅供学术交流、技术测试以及个人对图像生成算法的研究使用。
2. 禁止非法使用：用户在下载和使用这些模型时，必须严格遵守当地的法律法规。严禁使用这些模型侵犯他人的隐私、名誉、肖像权或其他合法权益。不得将其用于制造或传播虚假信息、欺诈活动或任何不道德的目的。
3. 侵权通知与删除：本仓库模型仅限非商业研究分享。如果您是版权所有者或授权代理人，并认为本仓库中的任何内容侵犯了您的权利，请直接与我联系。核实后，我将立即审查并毫不拖延地删除相关的侵权内容。
4. 内容合规提示：请注意，某些基础模型（如 Pony）在特定提示词方面可能具有较高的开放性。用户需全权负责对生成内容的合规性进行过滤和审查。
5. 责任限制：作为这些实验性模型的创建者/测试者，我对因使用本仓库而产生的任何直接或间接的法律责任、损失或纠纷概不负责。任何生成的图像及其后续产生的一切后果，均由用户自行承担全部责任。

---