V4推荐使用下面四个模型<a target="_blank" rel="ugc" href="https://civarchive.com/models/354666/starry-xl-kohaku-delta">Starry XL [kohaku delta] - v1.0 | Stable Diffusion Checkpoint | Civitai</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/332076/kohaku-xl-delta">Kohaku-XL Delta - rev1 |稳定扩散检查点 |奇维泰</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/257749?modelVersionId=290640">Pony Diffusion V6 XL - V6 (start with this one) | Stable Diffusion Checkpoint | Civitai</a><a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v3">Animagine XL V3 - v3.0 | Stable Diffusion Checkpoint | Civitai</a><hr />kohaku_delta使用<a target="_blank" rel="ugc" href="https://civarchive.com/models/332076/kohaku-xl-delta">Kohaku-XL Delta - rev1 |稳定扩散检查点 |奇维泰</a>使用<a target="_blank" rel="ugc" href="https://civarchive.com/models/260267/animagine-xl-v3">Animagine XL V3 - v3.0 | Stable Diffusion Checkpoint | Civitai</a>底模训练需要比较复杂的tag才能出比较好的效果Train using Animagine XL V3 - v3.0 | Stable Diffusion Checkpoint | Civitai base model.Complex tags are required to achieve optimal results

Files with SHA256: 47d6cd138e8a1cf021fcbba6e196944b9b0df6a0b0a32b4d6ff1fd2757af73b8