|
--- |
|
license: unknown |
|
--- |
|
|
|
<div align="center"> |
|
<h1 style="font-size: 2.5em;">Ai2Ai_v1</h1> |
|
</div> |
|
|
|
<div style="text-align: center; margin-top: 1.5em;"> |
|
<div style="display: inline-block; width: 45%;"> |
|
<a href="https://cdn.discordapp.com/attachments/1019446913268973689/1131771684031053834/00035-Niako_V3_fp16_real_3389039481.png"> |
|
<img class="custom-image" src="https://cdn.discordapp.com/attachments/1019446913268973689/1131771684031053834/00035-Niako_V3_fp16_real_3389039481.png" alt="Example 1"> |
|
</a> |
|
</div> |
|
<div style="display: inline-block; width: 45%;"> |
|
<a href="https://cdn.discordapp.com/attachments/1019446913268973689/1131771683649368224/00012-SatharielV1_3181298868.png"> |
|
<img class="custom-image" src="https://cdn.discordapp.com/attachments/1019446913268973689/1131771683649368224/00012-SatharielV1_3181298868.png" alt="Example 2"> |
|
</a> |
|
</div> |
|
</div> |
|
|
|
## 🌟 Model Details |
|
|
|
- **Model Name:** Ai2Ai_v1 |
|
- **Description:** A LoRA trained on AI-generated images sourced from Pinterest. |
|
- **Version:** v1 |
|
- **Release Date:** I don't remember. |
|
- **Framework:** Kohya Trainer Colab |
|
|
|
## 🌍 Intended Use |
|
|
|
This LoRA is designed for generating stunning anime girls with incredible creativity. It excels in generating detailed facial features and captivating hats. However, it's not optimized for rendering full body and clothing designs. |
|
|
|
## 📊 Performance |
|
|
|
- **Accuracy:** High on face and hat generation, lower on body details |
|
- **Precision:** High on face and hat generation, lower on body details |
|
|
|
## ⚡ Limitations and Bias |
|
|
|
- **Limitations:** This LoRA model is relatively small, resulting in the generation of somewhat identical faces. |
|
- **Bias Considerations:** Beware of potential artifacts such as "jpeg artifacts," "cheek bulge," and the model's potential to be overly powerful in certain aspects. Put these in negative prompts. |
|
## 🎯 Training Data |
|
|
|
- **Data Sources:** Images from Pinterest |
|
- **Data Size:** 82 images, approximately 12 MB |
|
- **Data Preprocessing:** AI-generated images carefully curated for training quality |
|
--- |
|
|
|
<div align="center"> |
|
<h1 style="font-size: 2.5em;">Ai2Ai_v2</h1> |
|
</div> |
|
|
|
<div align="center"> |
|
<h1 style="font-size: 1.0em;">Never worked for me, thanks.</h1> |
|
</div> |
