929721518本人的qq小群群號，有什麼不會的關於tpony的問題可以進來問。記得備註c站哦

模型已經內置vae了，不需要額外添加vae

The model already has included vae, there is no need to add additional vae

最佳的出圖策略是適中的分辨率開高清修復，而不是直接使用大分辨率直出

The best generate strategy is to use high-fix at a moderate resolution, rather than directly using high-resolution direct output

[未認證]Tonade正在創作T-ponynai3模型作者，c站id：Tonade， | 愛發電 (afdian.net)

這裡是愛發電的贊助通道，覺得模型好用且有餘力的話可以支持一下！萬不要勉強，感謝你們的每一份支持，會繼續探索怎麼把模型練好的!

(33) T-ponynai3-v5 - （權重修改版本） | Stable Diffusion Checkpoint | 吐司 tusi.cn (tusiart.com) tusiart(china version tensor) 線上生成連結

(因模型只能同時存在於 Tusi 和 Tensor，建議在 Tusi 使用。如使用中有任何問題，請多指教）

v5版本新增了4個style，可以透過style_1到style_4來微調畫面細節（理論上是這樣，實際效果較玄學）

V5 version 新增4種風格，可透過style_1至style_4細調圖片細節（理論如此，但實際效果較玄學或較弱）

本模型完美支援由ponyv6為底模訓練的模型，ani3，sdxl1.0的lora在某種程度上也能適配

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.

基於v4.1的圖像修補測試（這部分在之前版本中被忽略）

Image inpaint testing based on v4.1 (this is a previously overlooked part)

pony是神，兼容性滿分。本模型支持ani、pony的lora

必備前置效果詞與ponydiffusion相同

positive:(score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up)

或者 (score_9,score_8_up,score_7_up)

負面詞建議加入：

negative: (score_4,score_3,score_2,score_1),

亦可加入常見的nai系列負面詞，例如：

negative: worst quality, bad hands, bad feet

希望你喜歡 ᕕ(◠ڼ◠)ᕗ 基於 nai3 和 ponyv6

訓練須知：v1 使用了94張，v2 用了119張，v3 用了348張，v3.5 使用了474張由 nai3 生成的圖片，將訓練的 lora 融入底模進行微調，pony 支援的畫師 tag 全部支持，使用兩個以上畫師 tag 可能導致背景崩潰，目前發現能生成原神角色，其他不明。對此模型測試不多，驚嘆於其對nai3畫風的復刻。底模為 T-anime-xl、ponyv6 及 ani3 融合模型，尚未發布。

使用的訓練顯卡為我自己的3090，v1至v3分別使用7小時、12小時、35小時及47小時

訓練說明：合併Lora，v1用94張圖片，v2用119張，v3用348張，v3.5用474張，皆為nai3生成，用於基底模型微調。pony支援ponyv6所有畫師tag，nai3無新增畫師tag。超過兩個畫師tag可能背景崩潰。現已發現能生成原神角色，不確定其他角色未多做測試。驚嘆於對nai3畫風的再現。底模為T-anime-xl、ponyv6及ani3融合模型，尚未發布。

我使用自身3090顯卡進行訓練，v1至v3.5耗時分別為7、12、35及47小時。

v1

一次有趣的嘗試

An interesting attempt

v2

在v1基礎上略增訓練集，歷經約30小時的參數試誤，但畫風仍有過擬合，如雙肚臍眼及雜亂頭髮

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 hair

v3

v3的肢體較v2更佳，對footfocus理解更深，可生成視覺衝擊強烈且視角困難的腳，頭髮的AI感低於v2，因v2訓練集過少，頭髮部分有過擬合，v2偶爾出現的雙肚臍眼問題也消失。總體而言，三倍於v2的訓練集及更大dim參數使畫風自然擬合，長prompt下表現遠優於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.

v3.5

在此版本中，對質量詞要求不嚴格，可完全不使用pony美學評分質量詞作出圖。測試中偶爾出現無意義色塊，僅需將美學評分質量詞替換為1.5常用質量詞，如score_1、score_2改為worst quality。本版本加入約150張訓練集以平衡並充實畫風，減少學習曲線初始斜率，降低過擬合，適配更多lora及奇思妙想的提示詞。整體而言，此版本比v3更自由，對男性表現遠超v3，部分提示下色彩及畫風不再過分鮮豔及油膩。

In this version, the requirements for quality words are not so strict, you can completely not to use the quality words of pony's aesthetic score to plot the picture, and occasionally there will be a situation where the picture generates meaningless color blocks in the test, you only need to replace the quality words of the aesthetic score with 1.5 commonly used quality words, such as score_1, score_2 replace it with worst quality. In this version, I added about 150 more training sets to balance and enrich the art style, and reduced the initial slope of the learning curve, which makes this model less overfitted and can be adapted to more lora and whimsical prompts. Overall, this version is a freer version than the v3 version, and this version is much stronger than the v3 version, and the colors and style of painting under some hints are not so bright and greasy.

v4

版本使用798張圖片訓練素材，3090顯卡訓練90小時。較v3.5在某些提示下構圖及部位刻畫更準確，如手指重影與部分身體重疊。以中等及稍短prompt為主要訓練目標，取消pony美學分質量詞後，圖像質量較v3.5大幅提升，畫質偏向平面而非立體，更接近經典動漫畫風。ponyv6微調圖片數量測試接近尾聲，下一步將著手prompt標籤，嘗試在pony有限訓練素材中加入更多可控prompt（如加入美學評分，目前訓練邏輯仍用主流質量詞覆蓋pony美學分質量詞），持續增添合適新素材，如場景與更多足部素材（v4足部素材稍顯不足）。

This version used 798 images as training materials and trained for 90 hours using a 3090 graphics card. This version has a more accurate composition and depiction of certain parts in certain prompts compared to v3.5, such as ghosting of fingers and overlapping of some body parts. In terms of prompts, my main training goal is to use medium and slightly shorter prompts, as nobody likes to write a long string of prompts to generate high-quality images, right? After removing the quality prompt of Pony's aesthetic score, the image quality has been significantly improved compared to v3.5, and the resulting quality tends to be more flat rather than three-dimensional, closer to the classic anime style. The testing of the fine-tuning effect of Ponyv6 on the number of images is nearing completion. The next step is to start with the training labels of prompts and try to add more adjustable prompts to Pony's limited number of single training materials (such as adding aesthetic scores, the current training logic still uses mainstream quality words to cover Pony's aesthetic score quality words), and continue to add suitable new training materials, such as scene training materials and more foot training materials (v4's foot training materials seem to be a bit scarce).

v4.1

向各位用戶道歉在這麼短時間內又推出新版本，這十分考驗電腦的記憶體及網絡速度。O_O

Firstly, I would like to apologize to all users for the release of a new version in such a short period of time, which greatly tests the computer's memory and network speed. O_O

此新版本基於v4肢體調試版，因v4肢體效果難控，手部完美率未達預期。我與朋友木貓貓貓對v4作了調整改善，最終令v4.1肢體達標，我會放出幾張xy圖清晰展示v4.1相較v4在相同參數下的改進。

This new version is based on the limb debugging version of v4. Due to the difficulty in controlling the limb effects of v4, the perfection rate of the hands did not meet my testing expectations in the past few days. So my friend 木貓貓貓 and I made some adjustments and improvements to v4, which ultimately made the limbs of v4.1 meet my expectations. I will release several xy graphs to clearly show the improvement of v4.1 compared to v4 under the same parameters.

v5

此版本訓練素材減少，因v4失利，我推動另一項目，從較小顯存佔用角度測試想法，訓練四個適配T-ponynai3畫風的lora，原始模型亦上傳至civitai。適配測試完成後，開始將這四組不同畫風作為添加劑訓練入T-ponynai3-v5。驚喜的是，v5線條質感提升明顯，應因訓練了細膩素材。打標使用style_1至style_4提示詞，遺憾不知原因，四個畫風未分離或效果微弱，卻良好融合入原畫風。雖未達多畫風支持，但有效提升原nai3畫風質感一階，或許下版本可嘗試更進一步。（我喜愛遊戲，每次訓練不能玩電腦遊戲對我太難）

The training materials for this version have been reduced. Due to the failure of v4, I launched another project to test my idea from a small perspective of memory usage, which is to train four different art styles of Lora adapted to T-ponynai3. Of course, the original model was also uploaded to Civitai. After testing the adaptability, I started training these four different art styles as additives into T-ponynai3-v5. Surprisingly, The line texture of v5 has improved to a high level, probably because I trained a very delicate material. For the marking of these four art styles, I used the prompt words from style_1 to style_4. Unfortunately, for some reason, these four art styles were not separated or the effect was weak, but rather integrated well into the original art style. Although it did not achieve the goal of supporting multiple art styles, it effectively elevated the texture of the original Nai3 art style to a higher level. Perhaps the next version can try to take it even further. (I really enjoy playing games, and it's too difficult for me to play computer games every time I train.)

關於v5版本的一些問題總結。

1，lora兼容性與肢體、眼睛模糊問題。lora兼容性因本次訓練最終權重使用較高，部分情況下出現過擬合。優化版本降低相應權重，肢體崩壞率與部分lora兼容稍有改善。眼睛模糊應因訓練style_1，原素材眼睛模糊，可用style_3或4改善。

2，體積光曝光問題。測試時未遇此問題，原因應為使用noise offset訓練參數，提高模型對光提示詞的敏感度，相同權重的光提示詞生成結果較亮。建議嘗試不使用括號及數字提升權重，因sdxl對提示詞敏感，可嘗試多次重複相同提示詞以避免極端結果。使用此參數旨在修復少量提示詞生成結果偏黃問題，附上幾張對比圖供參考。

3，模型複雜度下降問題。理論及實測均顯示，v5比前版更乾淨多元，在部分提示詞作用下獲得更精準表現，附數張對比圖。訓練集未用過分複雜素材，因過複雜圖像易過擬合，導致細節缺失。

目的：希望得到與前版本差異顯著模型，而非幾乎一樣的模型。此次各位反饋為良好試錯機會，獨自試錯耗費成本。下版本嘗試增素材量，使不同畫風能良好融合與分離，用特定prompt切換畫風，或需新訓練技術。感謝反饋！

Summarize some issues regarding the v5 version.

1, Lora compatibility and issues with limbs and blurred eyes. Lora compatibility is that I used too much final weight for this training, and in some cases, overfitting may occur. This optimized version is the one that reduces the corresponding weight, and the limb collapse rate and compatibility with some Loras should be better. I have run several comparison charts of Loras trained with v4.1 for reference. The problem of blurred eyes should be the reason why I trained style_1. The eyes in the original material used are blurry, and can be improved by using style_3 or 4.

2. Exposure issues with volume light. I did not encounter this issue during testing, and the reason for it should be that I used the noise offset training parameter to increase the sensitivity of the model to light related prompt words, resulting in brighter results when the same weight of light prompt words were used. I suggest trying not to use parentheses and numbers to increase the weight. Due to the sensitivity of sdxl to prompt words, you can try repeating the same prompt words multiple times to avoid extreme results. At the same time, using this parameter is to fix the problem of generating yellow results under a small number of prompt words. I have run several comparison graphs for reference.

3. The problem of reduced model complexity. In theory and in practice. V5 should be a cleaner and more diverse model than the previous version, and with the help of some prompts, it should be able to achieve more accurate performance. Similarly, I ran several comparison charts for comparison. This training set did not use overly complex materials because I believe that overly complex images tend to overfit the results, which inevitably leads to a certain degree of detail loss.

Purpose: I hope to obtain a model that is significantly different from the previous version, rather than releasing a model that is almost identical to the previous version. This feedback from everyone is a great opportunity for trial and error, and I really don't have any trial and error costs on my own. In the next version, I will try to increase the amount of materials for different art styles, so that the art styles of different materials can be well integrated and separated. Using specific prompts to switch art styles may require some new training techniques. Thank you for your feedback!