T-ponynai3

模型已经内置vae了，不需要额外添加vaeThe model already has included vae, there is no need to add additional vae本模型完美支持由ponyv6为底模训练的模型，ani3，sdxl1.0的lora也能在某种程度上适配This model perfectly supports lora trained with ponyv6 as the base model, and the Lora of ani3 and sdxl1.0 can also be adapted to some extent.pony是神，兼容性满分。本模型支持ani，pony的lora必备前置效果词和ponydiffusion一样positive:(score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up)OR (score_9,score_8_up,score_7_up)负面可加：negative: (score_4,score_3,score_2,score_1),也可以加正常的nai系负面词，例如：negative: worst quality, bad hands, bad feethope u like it ᕕ(◠ڼ◠)ᕗ base on nai3 and ponyv6训练须知：v1使用了94张，v2用了119张，v3用了348张，nai3生成的图片,训练的lora融进底模进行微调，pony支持的画师tag都支持，使用两个以上的画师tag可能会导致背景崩溃，目前发现能生成原神的角色，其他的不知道了，对于这个模型我测试的也不多，惊叹于其对于nai3的画风复刻中。底模是T-anime-xl和ponyv6以及ani3的融合模型，并未发布。使用的训练显卡是我自己的3090显卡，v1到v3分别使用了7小时，12小时，35小时。Training Instructions：Merge Lora used 94 pictures for v1, 119 pics for v2, 348 pics for v3, which generated by NAI3 to train into the basemodel for fine-tuning,Pony supports all artist tags,Using more than two artist tags may cause background crashes,At present, it has been found that characters that can generate Genshin Impact.I don't know the others.I haven't tested much for this model.,Marvel at its reproduction of the painting style of NAI3.The base model is a fusion model of T-anime-xl and ponyv6 and animage3, which has not been releasedThe training graphics card I used was my own 3090 graphics card, which was used for 7 hours, 12 hours, and 35 hours from v1 to v3, respectively.v1一次有趣的尝试An interesting attemptv2在v1的基础上略微增加了训练集，并经历了30小时左右的参数试错，但是训练出来的画风仍然具有一些过拟合，例如双重肚脐眼以及杂乱的头发On the basis of v1, the training set was slightly increased and went through about 30 hours of trial and error, but the trained art style still had some overfitting, such as double navel eyes and messy hairv3v3的肢体会比v2的更好，对于footfocus的理解v3可以生成视觉冲击更大的脚，也更高难度的透视视角，v3的头发的ai感也比v2要弱，因为v2的训练集太少了，所以头发部分会有些过拟合，而且v2偶尔会出现的双肚脐眼也没了。总体来说三倍于v2训练集的大小以及更大的dim参数使得画风拟合的更加自然，而且在长prompt下的表现力远远强于v2。The limbs of v3 are better than those of v2. In terms of understanding footfocus, v3 can generate feet with greater visual impact and higher difficulty perspective. The AI feeling of v3's hair is also weaker than that of v2, because v2 has too little training set, so the hair part may be slightly overfitting, and the occasional double navel eyes that appear in v2 are also gone. Overall, three times the size of the v2 training set and a larger dim parameter make the art style fit more natural, and the performance is much stronger than v2 under long prompts.