Pony: People's Works + - v7_Animv4
æšå¥šããã³ãã
masterpiece, best quality, very aesthetic
score_9, score_8_up, score_7_up, score_6_up, score_5_up
masterpiece, best quality, very aesthetic, hatsune miku, 1girl, pink hair scrunchie, solo, (licking:0.8), dark hair, black nightgown, long hair, frills, blue eyes, short sleeves, holding candy apple, holding rose, glowing candy apple, half-closed eyes, black background, looking at viewer, white collared shirt, colorful, brown vest, glowing hair, pleated skirt, long skirt, portrait, sitting, from side, knees up, upper body, day, Eleanor \(people's works\), boat, river, cloud, blue sky, from below
æšå¥šãã¬ãã£ãããã³ãã
low quality, displeasing
score_3, score_2, score_1
low quality, displeasing, hair intakes, shiny hair
æšå¥šãã©ã¡ãŒã¿
samplers
steps
cfg
ãã³ã
v7ããŒãžã§ã³ã¯ããŒã¿æ§é ãšãã¬ãŒãã³ã°æŠç¥ã®èª¿æŽãããã以åã®ããŒãžã§ã³ãããå®å®æ§ãäœäžããå¯èœæ§ããããŸãã
åããã©ã¡ãŒã¿ã§ããªã³ã©ã€ã³ãžã§ãã¬ãŒã¿ãŒã«ãã£ãŠæ§èœã倧ããç°ãªããŸãã
ã¢ãã«ã«ã¯ç¹å®ã®ç»å®¶ã«äŸåããããŒã¿ãã¿ã°ãå«ãŸããŠããããç¹å®ã®ç»é¢šã®åœ±é¿ãé¿ããŠããŸãã
åçšå©çšãæ€èšãããŠãŒã¶ãŒã¯ãæ¬ã¢ãã«ãšå ±ã«äœ¿çšãããã§ãã¯ãã€ã³ããLoRAã®ã©ã€ã»ã³ã¹ã«æ³šæããŠãã ããã
ãæ³šæ | Note
v7ããŒãžã§ã³ã¯ããŒã¿ã»ããæ§é ã«å€§å¹ ãªèª¿æŽãå ããç°ãªããã¬ãŒãã³ã°ãã©ã¡ãŒã¿ãšæŠç¥ã䜿çšããŠãããããv7ã¯åŸæ¥ã®ããŒãžã§ã³ããå®å®æ§ã«å£ãå¯èœæ§ããããŸãã
v7 version has undergone significant structural adjustments to the dataset, and utilizes different training parameters and strategies. As a result, v7 may be less stable than the previous versions.
civitAIã®ãªã³ã©ã€ã³ãžã§ãã¬ãŒã¿ãŒã§ã®v-predã¢ãã«ã®ããã©ãŒãã³ã¹ã¯ãTensorArtã®ãªã³ã©ã€ã³çæãšå šãç°ãªããåããã©ã¡ãŒã¿ã§ãåçŸã§ããŸãããçç±ã¯äžæã§ãâŠ
The v-pred model's performance on the CivitAI online generator is completely different from online generation on TensorArt. The results are entirely unreproducible with a same parameters. I have no idea why...
TensorArt ããŒãžã§ã³ CivitAI åãã©ã¡ãŒã¿ç CivitAIäžã§ ããé«ãéã¿ä»ãç
ã¯ã€ãã¯ã¹ã¿ãŒã | Quick Start
ããã¯äœïŒ | What is this?
ããã¯åäœã®ããŒã¿ã»ãããåºã«éçºãããç»åå質åäžçšLoConã§ãçŽ90%-95%ã®ç»åããŒã¿ãCivitAIã®æçš¿ç»åã§ãã
æ¬ã¢ãã«ã¯ç»å®¶ã¿ã°ã䜿ãããæå°éã®å質ããã³ããã§æ¯èŒçå®å®ããç»åå質ãå®çŸããããŒã¯ã³ã¹ããŒã¹ã®ç¯çŽãå¯èœã«ããŸãããŸãã¢ãã«ã®åºæã®çææ¬ ç¹ã®äžéšãä¿®æ£ããŸãïŒãã ãæã¯é€ãïŒã
ããŒã¿ã»ããã®ç¹æ§ã«ããçæãããç»åã¯Pony颚ã®è³ªæãæã¡ãŸãããç¹å®ã®ç»å®¶ãã¹ã¿ã€ã«ãææ³ãæãããã®ã§ã¯ãªããããããã³ããããã§ãã¯ãã€ã³ãæ¡ä»¶ã«ãã埮åŠãªç»é¢šã®éããçŸããããšããããŸãã
This is a generation quality LoCon developed based on the dataset from the previous work. About 90%-95% of the image data comes from CivitAI.
It allows models to achieve relatively stable image quality without artist tags or using long quality prompts, freeing up more token space. Additionally, it can fix some inherent generation flaws of the model. (except for hands)
Due to the dataset selection, the generated images exhibit a Pony-like style. However, since it does not reference any specific artist, style, or painting technique, there may be subtle stylistic variations depending on different prompts and checkpoint conditions.
äœ¿ãæ¹ | Usage
å質ã¿ã°ããŒã¹ã®ã¢ãã«ã®å Žåã
For models based on quality tags,
ããžãã£ã:
masterpiece, best quality, very aestheticãã¬ãã£ã:
low quality, displeasingPonyã¹ã³ã¢äœç³»ã¢ãã«ã®å Žåã
For models based on Pony scores,
ããžãã£ã:
score_9, score_8_up, score_7_up, score_6_up, score_5_up,ãã¬ãã£ã:
score_3, score_2, score_1, ããŒã¿ã»ããã®åºå žãšã©ã€ã»ã³ã¹ | Dataset Source & License
ããŒã¿ã»ããå ã®ãã¹ãŠã®ç»åã¯ãèè ã«ããæäœæ¥ã§éžå¥ãåé¡ã泚éãä»ãããããã®ãã¡æ°çŸæã¯æåã§ç·šéã»ä¿®æ£ãããŠããŸãã
æ¬ã¢ãã«ã¯ç¡æãã€ãªãŒãã³ãœãŒã¹ã§ããŠãŒã¶ãŒã¯å人ã®ç«¯æ«ã§èªç±ã«å±éå¯èœã§ããèè ã¯ã¢ãã«ã®è²©å£²ããå ±é ¬ãåããŠããŸãããèè ã¯æ¬ã¢ãã«ã®åçšç»åçæãµãŒãã¹ãåçšç»åçæå©çšãå¶éããŸãããããã§ãã¯ãã€ã³ããä»ã®LoRAã®ã©ã€ã»ã³ã¹èŠçŽã«ã¯æ³šæããŠãã ããã
ããŒã¿ã»ããã®çŽ90%-95%ã¯AIçæç»åã§ãããæŠå¿µè£å®ã®ããå ¬å ±ã¡ãã£ã¢ããã¥ãŒã¹ã¡ãã£ã¢ãåºçç©ããåéãã250æä»¥äžã®ç»åãå«ãŸããŠããŸããå°æ¥çãªããŒãžã§ã³ã§é 次眮ãæãäºå®ã§ããåçšå©çšãç®çãšãããŠãŒã¶ãŒã¯ãªã¹ã¯ã«ã泚æãã ããã
æ¬ããŒã¿ã»ããã«ã¯åå¥ã®ç»å®¶ããŒã¿ãç»å®¶æ å ±ã®æ³šéã¯å«ãŸããŠããŸããïŒAIã®èª€ã¿ã°ä»ãã¯æé€ã§ããŸããïŒã
ãŸããæ¬ã¢ãã«ã¯ã¯ããŒãºãåçšå©çšãã¢ãã«è²©å£²ãã¯ããŒãºãåçšã¢ãã«ãžã®çµ±åãçŠæ¢ããŸãããªãŒãã³ãœãŒã¹ã®çµ±åã¢ãã«ã«ããçæãµãŒãã¹å©çšã«ã¯å¶çŽã¯ãããŸããããçµ±åã¢ãã«ã®åºå žæç€ºãæšå¥šããŸãã
Every image in the dataset has been manually selected, categorized, and annotated by the author. Additionally, hundreds of the images have been manually edited and corrected.
This model is free and open-source model, allowing users to deploy it on their personal devices. The author does not receive any compensation from selling the model. The author does not impose restrictions on using this model for commercial image generation services or generating images for commercial purposes. However, please be mindful of the license restrictions of the Checkpoint and other LoRAs used alongside this model.
Approximately 90%-95% of the dataset consists of AI-generated images. However, around 250+ images have been collected from public media, news outlets, and publications to supplement concepts. Future versions will gradually replace these materials. Users with commercial intentions should be aware of the potential risks.
This dataset does not include training data from any individual artist, nor does it contain explicit artist attributions (though AI mistagging cannot be entirely ruled out).
Additionally, this model is not permitted for use in closed-source commercial applications, model resales, or merged into closed-source commercial models. There are no restrictions on open-source merged models being used for image generation services, but it is recommended to credit the sources of any merged models.
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





