该模型受到模型大佬LEOSAM的启发和交流，通过“差异训练法”训练得来。<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/64b63537-341d-461c-bc38-a3c0ce772c80/width=525/64b63537-341d-461c-bc38-a3c0ce772c80.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d2a2df8d-66e0-4bd1-9577-28bdc93a2a22/width=525/d2a2df8d-66e0-4bd1-9577-28bdc93a2a22.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fbd8b61d-5ebb-40ca-a879-68863747fe93/width=525/fbd8b61d-5ebb-40ca-a879-68863747fe93.jpeg" />不同的大模型会出现不同的结果，受限于当前技术，还是无法完全固定住人物的线条，所以图一是通过controlnet的canny得来，图二应该是使用anytingV5，大家也可以尝试使用其它模型。Different large models may produce different results, and due to current technology, it is still not possible to completely fix the lines of characters. Therefore, Figure 1 is obtained through the Canny of Controlnet, and Figure 2 should use AnytingV5. You can also try using other models.合作邮箱：1045117761@qq.com

Outline |Line draft| 线稿 自动褪色|Automatic coloring

OutlineSuperV9.safetensors

v1.0

Line art - automatic coloring

The model was inspired and communicated by LEOSAM, the model leader, and trained through a “differential training method.” Figure 1 effect can be achieved with XYZ and ControlNet <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/64b63537-341d-461c-bc38-a3c0ce772c80/width=525/64b63537-341d-461c-bc38-a3c0ce772c80.jpeg" alt="" data-href="" style=""> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d2a2df8d-66e0-4bd1-9577-28bdc93a2a22/width=525/d2a2df8d-66e0-4bd1-9577-28bdc93a2a22.jpeg" alt="" data-href="" style=""> <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/fbd8b61d-5ebb-40ca-a879-68863747fe93/width=525/fbd8b61d-5ebb-40ca-a879-68863747fe93.jpeg" alt="" data-href="" style=""> Different large models will have different results. Due to current technology, it is still not possible to completely fix the character's line, so Figure 1 is obtained through Controlnet's Canny. Figure 2 should use AnytingV5, and everyone can try using other models. Different large models may produce different results, and due to current technology, it is still not possible to fix the lines of characters. Remains, Figure 1 is presented through the Canny of Controlnet, and Figure 2 should use AnytingV5. You can also try using other models. Cooperation email: 1045117761@qq.com

Files with SHA256: 0b45b0ccf4f4739f8f2509b76bbc4f9290b28184d05b31200fc69129c96be6e3