Tponynai3 - v55
é¢é£ããŒã¯ãŒãïŒã¿ã°
æšå¥šããã³ãã
score_9,score_8_up,score_7_up
score_9,score_8_up
æšå¥šãã¬ãã£ãããã³ãã
score_4,score_3,score_2,worst quality, bad hands, bad feet
score_3,score_2,ugly,bad feet
æšå¥šãã©ã¡ãŒã¿
samplers
steps
cfg
clip skip
resolution
other models
æšå¥šãã€ã¬ãŸãã©ã¡ãŒã¿
upscaler
upscale
steps
denoising strength
ãã³ã
äžè§£å床ã§é«åè³ªè£æ£ã䜿çšãããšæè¯ã®çµæãåŸãããŸãã
ç®ã®ãã£ããŒã«ãæ¹åããããã«style_3ãŸãã¯4ã詊ããŠãã ããã
929721518æ¬äººçqqå°çŸ€çŸ€å·ïŒæå¥äžäŒçå ³äºtponyçé®é¢å¯ä»¥è¿æ¥é®ãè®°åŸå€æ³šcç«åŠ
ã¢ãã«ã«ã¯ãã§ã«VAEãå«ãŸããŠããã远å ã®VAEã远å ããå¿ èŠã¯ãããŸãã
The model already has included vae, there is no need to add additional vae
æè¯ã®çææŠç¥ã¯å€§è§£å床ã®çŽåºãã§ã¯ãªããäžè§£å床ã§é«åè³ªè£æ£ã䜿çšããããšã§ã
The best generate strategy is to use high-fix at a moderate resolution, rather than directly using high-resolution direct output
(33) T-ponynai3-v5 - ïŒæéä¿®æ¹çæ¬ïŒ | Stable Diffusion Checkpoint | ååž tusi.cn (tusiart.com) tusiart(china version tensor) online generate link
(Because the model can only exist on both Tusi and Tensor simultaneously, it is better to use it in Tusi. If there are any issues with its use, please point them out more to meïŒ
v5ããŒãžã§ã³æ°ãã«4ã€ã®ã¹ã¿ã€ã«ã远å ãããstyle_1ããstyle_4ãéããŠç»åã®ãã£ããŒã«ã埮調æŽã§ããŸãïŒçè«äžã¯ããã§ãããå®éã®å¹æã¯ããç¥ç§çã§ãïŒã
V5ããŒãžã§ã³ has added 4 new styles, which can be used to fine tune the details of the image through style_1 to style_4 (theoretically, this is the case, but the actual effect is more mystical or lower)
æ¬ã¢ãã«ã¯ponyv6ãåºã«èšç·ŽãããLoRaãå®ç§ã«ãµããŒãããani3ãšsdxl1.0ã®LoRaãããçšåºŠé©åããŸãã
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.
åºäºv4.1çåŸçåŸæµè¯ïŒè¿æ¯åšä¹åçæ¬é被応ç¥çéšåïŒ
Image inpaint testing based on v4.1 (this is a previously overlooked part)




ponyã¯ç¥ã§ãããäºææ§ã¯æºç¹ã§ããæ¬ã¢ãã«ã¯aniãponyã®LoRaããµããŒãããŠããŸãã
å¿ å€å眮ææè¯åponydiffusionäžæ ·
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)
èŽé¢å¯å ïŒ
negative: (score_4,score_3,score_2,score_1),
ãŸããéåžžã®naiç³»ã®è² ã®åèªã远å ã§ããŸããäŸïŒ
negative: worst quality, bad hands, bad feet
hope u like it á(â ÚŒâ )á ããŒã¹ã¯nai3ãšponyv6
èšç·Žã«ã€ããŠïŒv1ã§94æãv2ã§119æãv3ã§348æãv3.5ã§474æã®ç»åã䜿çšããnai3ã§çæããç»åãåºã«LoRaãèšç·ŽããŠããŒã¹ã¢ãã«ã«åŸ®èª¿æŽããŸãããponyv6ãæ¢ã«æã£ãŠããã¢ãŒãã£ã¹ãã¿ã°ã«ã¯ãã¹ãŠå¯Ÿå¿ããŠããŸãããnai3ãã远å ãããã¢ãŒãã£ã¹ãã¿ã°ã¯ãããŸããã2ã€ä»¥äžã®ã¢ãŒãã£ã¹ãã¿ã°ã䜿çšãããšèæ¯ã厩ããããšããããŸããçŸæç¹ã§ãåç¥ã®ãã£ã©ã¯ã¿ãŒãçæã§ããããšã確èªãããŠããŸããä»ã®ãã£ã©ã¯ã¿ãŒã«ã€ããŠã¯ç¢ºèªãããŠããŸããããã®ã¢ãã«ã®ãã¹ããããŸãè¡ã£ãŠããŸãããnai3ã®ç»é¢šã®åçŸæ§ã«æåãããããŸããããŒã¹ã¢ãã«ã¯T-anime-xlãponyv6ãani3ã®èåã¢ãã«ã§ãæªå ¬éã§ãã
䜿çšãããã¬ãŒãã³ã°çšã°ã©ãã£ãã¯ã¹ã«ãŒãã¯ç§ã®3090ã§ãv1ããv3.5ãŸã§ãããã7æéã12æéã35æéã47æé䜿ããŸããã
Training InstructionsïŒMerge Lora used 94 pictures for v1, 119 pics for v2, 348 pics for v3, 474 pics for v3.5,which generated by NAI3 to train into the basemodel for fine-tuning,Pony supports all artist tags which ponyv6 already have, but there is no any addition artist tag from nai3. 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 released
The training graphics card I used was my own 3090 graphics card, which was used for 7 hours, 12 hours, and 35 hours and 47 hours from v1 to v3.5, respectively.
v1
äžåºŠã®è峿·±ã詊ã¿
An interesting attempt
v2
v1ã®åºç€ã®äžã«ãã¬ãŒãã³ã°ã»ãããããå¢ãããçŽ30æéã®è©Šè¡é¯èª€ãçµãŸãããããã¬ãŒãã³ã°ãããç»é¢šã«ã¯ãŸã ããããã®éå°é©åããããäºéã®ãžããä¹±ãã髪ãªã©ããããŸãã
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
v3ã®è¢äœã¯v2ãããåªããŠãããfootfocusã®çè§£ã«ãããŠãv3ã¯èŠèŠçãªã€ã³ãã¯ãã倧ããè¶³ãçæã§ããããé£æåºŠã®é«ãé è¿æ³ã®èŠè§ãå¯èœã§ããv3ã®é«ªã®AIæã¯v2ãã匱ããªã£ãŠããŸããåå ã¯v2ã®ãã¬ãŒãã³ã°ã»ãããå°ãªãããããã髪ã®äžéšãéå°é©åããå¯èœæ§ããããv2ã§ææèŠãããäºéã®ãžããæ¶ããŸãããå šäœãšããŠãv2ã®ãã¬ãŒãã³ã°ã»ããã®èŠæš¡ãäžåã«ãããã倧ããªdimãã©ã¡ãŒã¿ã䜿çšããããšã§ãç»é¢šã®ãã£ããæãããèªç¶ã«ãªããé·ãããã³ããã§ã®è¡šçŸåãv2ãã¯ããã«äžåããŸãã
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
ãã®ããŒãžã§ã³ã§ã¯ãã¯ãªãªãã£ã¯ãŒãã«å¯ŸããèŠä»¶ã¯ããã»ã©å³æ Œã§ã¯ãªãããããŒã®çŸåŠã¹ã³ã¢ã®ã¯ãªãªãã£ã¯ãŒããå®å šã«äœ¿ããªãã§ç»åãçæããããšãã§ãããã¹ãäžã«ç»åãæå³ã®ãªãã«ã©ãŒãããã¯ãçæããç¶æ³ãçºçããããšãããããã®å Žåã¯çŸåŠã¹ã³ã¢ã®ã¯ãªãªãã£ã¯ãŒãã1.5ã®éçšã¯ãªãªãã£ã¯ãŒããäŸãã°score_1ãscore_2ãworst qualityã«çœ®ãæããã ãã§ãããã®ããŒãžã§ã³ã§ã¯ããã©ã³ã¹ãšç»é¢šã®å å®ãå³ãããã«ãçŽ150ã®ãã¬ãŒãã³ã°ã»ããã远å ããåŠç¿æ²ç·ã®åææçãæžå°ãããŸãããããã«ããããã®ã¢ãã«ã¯éå°é©åãå°ãªããªããããå€ãã®LoRaãåµé çãªããã³ããã«é©å¿ã§ããããã«ãªããŸããå šäœãšããŠããã®ããŒãžã§ã³ã¯v3ã«æ¯ã¹ãŠããèªç±ãªããŒãžã§ã³ã§ãããç·æ§ã®æåãv3ã«æ¯ã¹ãŠã¯ããã«åŒ·çã§ãäžéšã®ããã³ããäžã§ã¯è²åœ©ãç»é¢šãããã»ã©éå°ã«é®®ããã§æ²¹ã£ãœããããŸããã
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
ãã®ããŒãžã§ã³ã§ã¯798æã®ç»åããã¬ãŒãã³ã°çŽ æãšããŠäœ¿çšãã3090ã°ã©ãã£ãã¯ã¹ã«ãŒãã§90æéã®ãã¬ãŒãã³ã°ãè¡ããŸããããã®ããŒãžã§ã³ã¯ãç¹å®ã®ããã³ããäžã§ã®æ§å³ãšç¹å®ã®éšåã®æç»ãv3.5ã«æ¯ã¹ãŠããæ£ç¢ºã§ãäŸãã°æã®ãŽãŒã¹ããäœã®äžéšã®éè€ãèæ ®ããŠããŸããããã³ããã«é¢ããŠã¯ãäžçšåºŠã®é·ããšããçãé·ãã®ããã³ãããäž»ãªãã¬ãŒãã³ã°ç®æšãšããŸããã誰ãé·ãããã³ãããæžããŠé«å質ãªç»åãçæããããšã¯æããŸããããïŒãããŒã®çŸåŠã¹ã³ã¢ã®å質ããã³ãããåé€ããåŸãç»åã®å質ã¯v3.5ãšæ¯èŒããŠå€§å¹ ã«åäžããçæãããå質ã¯ããå¹³é¢çã§ãç«äœçã§ã¯ãªããã¯ã©ã·ãã¯ãªã¢ãã¡ã¹ã¿ã€ã«ã«è¿ã¥ããŸãããPonyv6ã®åŸ®èª¿æŽå¹æã«å¯Ÿããç»åæ°ã®ãã¹ãã¯çµäºéè¿ã§ããæ¬¡ã®ã¹ãããã¯ããã³ããã®ãã¬ãŒãã³ã°ã©ãã«ããå§ããŠãPonyã®éãããåäžãã¬ãŒãã³ã°çŽ æã®æ°ã«ããã£ãšèª¿æŽå¯èœãªããã³ããã远å ããŠããããšã§ãïŒäŸïŒçŸåŠã¹ã³ã¢ã远å ãçŸåšã®ãã¬ãŒãã³ã°ããžãã¯ã¯äž»æµã®å質ã¯ãŒãã§Ponyã®çŸåŠã¹ã³ã¢å質ã¯ãŒããã«ããŒããŠããïŒããŸããé©åãªæ°ãããã¬ãŒãã³ã°çŽ æãç¶ç¶çã«è¿œå ããäºå®ã§ããäŸãã°ã·ãŒã³ã®ãã¬ãŒãã³ã°çŽ æãè¶³ã®ãã¬ãŒãã³ã°çŽ æïŒv4ã®è¶³ã®ãã¬ãŒãã³ã°çŽ æã¯ã©ãããäžè¶³ããŠããããã§ãïŒã
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
ãã¹ãŠã®ãŠãŒã¶ãŒã®çæ§ã«ããããªã«çæéã§æ°ããããŒãžã§ã³ããªãªãŒã¹ããŠç³ãèš³ãããŸãããããã¯ãã³ã³ãã¥ãŒã¿ãŒã®ã¡ã¢ãªãšãããã¯ãŒã¯é床ã倧ãã«ãã¹ãããŸããO_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
ãã®æ°ããŒãžã§ã³ã¯v4ã®è¢äœãããã°ããŒãžã§ã³ã«åºã¥ããŠããŸããv4ã®è¢äœå¹æãå¶åŸ¡ããã®ãé£ãããããæã®å®ç§åºŠã¯ããæ°æ¥ã®ãã¹ãã®æåŸ ãæºãããŸããã§ãããããã§ãç§ãšç§ã®å人æšç«ç«ç«ã§v4ã«ããã€ãã®èª¿æŽãšæ¹åãå ããæçµçã«v4.1ã®è¢äœãç§ã®æåŸ ã«å¿ããŸãããv4ã®æ¹å床ãåããã©ã¡ãŒã¿ãŒäžã§çæãããç»åãšæ¯èŒããããã«ãããã€ãã®xyã°ã©ããå ¬éããŸãã
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 æšç«ç«ç« 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
ãã®ããŒãžã§ã³ã§ã¯ãã¬ãŒãã³ã°çŽ æãæžã£ãŠããŸããv4ã®å€±æã®ãããã¡ã¢ãªäœ¿çšã®å°ããªèгç¹ããã¢ã€ãã¢ããã¹ãããããã®å¥ã®ãããžã§ã¯ããéå§ããŸãããããã¯ãT-ponynai3ã«é©å¿ãã4ã€ã®ç°ãªãã¢ãŒãã¹ã¿ã€ã«ã®LoRaãèšç·Žããããšã§ããåœç¶ãå ã®ã¢ãã«ãCivitaiã«ã¢ããããŒããããŸãããé©åæ§ã®ãã¹ããå®äºããåŸããããã®4ã€ã®ç°ãªãã¢ãŒãã¹ã¿ã€ã«ãT-ponynai3-v5ã«å å€ãšããŠèšç·Žãå§ããŸãããé©ããããšã«ãv5ã®ã©ã€ã³ã®ãã¯ã¹ãã£ãå€§å¹ ã«åäžããŸãããããããéåžžã«ç¹çްãªçŽ æãèšç·Žããããã ãšæããŸãããããã®4ã€ã®ã¢ãŒãã¹ã¿ã€ã«ã®ããŒãã³ã°ã«ããstyle_1ããããstyle_4ããŸã§ã®ããã³ããã¯ãŒãã䜿çšããŸãããæ®å¿µãªãããäœããã®çç±ã§ããããã®4ã€ã®ã¢ãŒãã¹ã¿ã€ã«ã¯ããããåé¢ãããã广ã匱ãã£ããããŸããããå ã®ã¢ãŒãã¹ã¿ã€ã«ã«ããŸãçµ±åãããŸãããè€æ°ã®ã¢ãŒãã¹ã¿ã€ã«ããµããŒãããç®æšã¯éæãããŸããã§ããããå ã®nai3ã¢ãŒãã¹ã¿ã€ã«ã®ãã¯ã¹ãã£ã广çã«é«ããŸãããæ¬¡ã®ããŒãžã§ã³ã§ã¯ããã«é²ããããšãã§ãããããããŸãããïŒã²ãŒã ããã¬ã€ããã®ããšãŠã奜ãã§ãèšç·Žäžã«ã³ã³ãã¥ãŒã¿ã²ãŒã ããã¬ã€ã§ããªãã®ã¯é£ããã§ãïŒ
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.)
v5ããŒãžã§ã³ã«é¢ããããã€ãã®åé¡ãèŠçŽããŸãã
1ãLoRaã®äºææ§ãšè¢äœã®åé¡ããããŠãŒãããç®ã®åé¡ãLoRaã®äºææ§ã®æçµçãªéã¿ãä»åã®ãã¬ãŒãã³ã°ã«å¯ŸããŠããé«ããããããããã€ãã®ã±ãŒã¹ã§ã¯éå°é©åãçºçããå¯èœæ§ããããŸãããã®æé©åããŒãžã§ã³ã¯å¯Ÿå¿ããéã¿ãäœæžããããŒãžã§ã³ã§ãããè¢äœã®åŽ©å£çãäžéšã®LoRaãšã®äºææ§ãæ¹åãããã¯ãã§ããv4.1ã§èšç·Žãããç»é¢šã®LoRaã䜿çšããæ¯èŒå³ãããã€ãæ®ããŸããã®ã§ãåèã«ããŠãã ããããŒãããç®ã®åé¡ã¯ãstyle_1ãèšç·Žããããã§ãã䜿çšããå ã®çŽ æã®ç®ããŒãããŠãããããstyle_3ãŸãã¯4ã䜿çšããããšã§æ¹åãå¯èœã§ãã
2ãããªã¥ãŒã ã©ã€ãã®é²åºåé¡ããã¹ãäžã«ã¯ãã®åé¡ã«ééããŸããã§ããããã®åé¡ã®åå ã¯ç§ããã€ãºãªãã»ããã®ãã¬ãŒãã³ã°ãã©ã¡ãŒã¿ã䜿çšããŠå ã«é¢é£ããããã³ããã¯ãŒãã®ææåºŠãäžæãããããã§ãåãéã¿ã®å ã®ããã³ããã¯ãŒãã䜿çšããããšããæããçµæãšããå¯èœæ§ããããŸããç§ã¯éã¿ãå¢å ãããããã«æ¬åŒ§ãæ°åã䜿çšããªãããšããå§ãããŸããããã³ããã¯ãŒãã«å¯Ÿããsdxlã®æåºŠäžãåãããã³ããã¯ãŒããäœåºŠãç¹°ãè¿ããŠè©ŠããŠã極端ãªçµæãé¿ããããšãã§ããŸããåæã«ããã®ãã©ã¡ãŒã¿ãŒã䜿çšããããšã¯å°æ°ã®ããã³ããã¯ãŒãã§çæãããçµæãé»è²å³ãããåé¡ãä¿®æ£ããããã§ããç§ã¯ããã€ãã®æ¯èŒã°ã©ããæ®ã£ãŠåèã«ããŸããã
3ãã¢ãã«ã®è€éæ§ãæžå°ããåé¡ãçè«äžãå®éšçã«èšãã°ãv5ã¯ä»¥åã®ããŒãžã§ã³ãããããã¯ãªãŒã³ã§å€æ§ãªã¢ãã«ã§ããã¯ãã§ãããã€ãã®ããã³ããã®å©ããåããŠããç²Ÿç¢ºãªæ§èœãçºæ®ã§ããã¯ãã§ããåæ§ã«ãç§ã¯ããã€ãã®æ¯èŒã°ã©ããæ®ããŸããããã®ãã¬ãŒãã³ã°ã»ããã«ã¯ããŸãã«è€éãªçŽ æã¯äœ¿çšãããŠããŸããããªããªãç§ã¯é床ã«è€éãªç»åã§ã¯çµæãéå°é©åããåŸåããããããçšåºŠã®ãã£ããŒã«æå€±ãå¿ ç¶çã«å°ããŠããŸããšèããŠããŸãã
ç®çïŒç§ã¯ã以åã®ããŒãžã§ã³ãšå€§ããªéãã®ããã¢ãã«ãååŸããããšæã£ãŠããŸããã以åãšã»ãšãã©åãã¢ãã«ãçºå£²ããããããŸãããçããããã®ãã£ãŒãããã¯ã¯ã詊è¡é¯èª€ã®ããã®è¯ãæ©äŒã§ãããèªåã ãã§ã¯å®éã«è©Šè¡é¯èª€ã®ã³ã¹ããããããªãã§ããæ¬¡ã®ããŒãžã§ã³ã§ã¯ãç°ãªãç»é¢šã®çŽ æã®éãå¢ãããç°ãªãçŽ æã®ç»é¢šãããŸãèåãããåé¢ã§ããããã«ããããšèããŠããŸããç¹å®ã®ããã³ããã䜿çšããŠç»é¢šãåãæ¿ããããšãç®æããŠãããã€ãæ°ãããã¬ãŒãã³ã°ãã¯ããã¯ãå¿ èŠã«ãªããããããŸããããã£ãŒãããã¯ããããšãããããŸãïŒ
ã¢ãã«è©³çް
ã¢ãã«ã¿ã€ã
ããŒã¹ã¢ãã«
ã¢ãã«ããŒãžã§ã³
ã¢ãã«ããã·ã¥
äœæè
ãã£ã¹ã«ãã·ã§ã³
ã³ã¡ã³ããæ®ãã«ã¯ log in ããŠãã ããã














