Pony: People's Works + - v8_Illusv2.0Stable
æšå¥šããã³ãã
masterpiece,best quality,very aesthetic
collarbone, HDR, 8K, masterpiece, high contrast, best quality, very aesthetic, amazing quality, light smile, white hair, newest, long hair, volumetric lighting, 1girl, red eyes, (artist:incase:0.3), solo, sitting, (artist:tsuaii:0.3), holding phone, (realistic:1), sundress, (flat color:1.5), outdoors, bench, shopping bag, himuromizuki, garden, short hair, day, orange hair, pink hair, streaked hair, multicolored hair, hair between eyes, ahoge, pink eyes, hairclip, hand on hip, leaning forward, open mouth, smile, lens flare, gradient background, abstract background, yojifuku, witch, dress, pantyhose, hat
æšå¥šãã¬ãã£ãããã³ãã
low quality,displeasing
Base:bad quality, muted color, worst detail, low quality, worst quality, sketch, displeasing, censor, text, watermark, bad anatomy, artist name, signature
æšå¥šãã©ã¡ãŒã¿
samplers
steps
cfg
ãã³ã
åå®çã¹ã¿ã€ã«ã®å Žåããphotorealisticãã¿ã°ãäœãéã¿ã§äœ¿ãèçã調æŽããŠãã ããã
ããè¯ãå宿§ãæ±ããå Žåã¯ããrealisticãã¿ã°ãé«ãéã¿ã§äœ¿çšãããšå¹æçã§ãã
ãã®ã¢ãã«ã¯ç»åž«ããŒã¯ãŒããé·ãå質ããã³ãããªãã§å®å®ããç»è³ªãåºããããŒã¯ã³ã¹ããŒã¹ãç¯çŽããŸãã
髿¬¡å LoConçã¯å¹æã®åŒ·åºŠèª¿æŽããã容æã§æ±åèœåã匷åãããŠããŸãããããå€ãã®ã¹ãã¬ãŒãžãšèšç®ãªãœãŒã¹ãå¿ èŠãšããŸãã
æ¬ã¢ãã«ã¯ç¹å®ã¹ã¿ã€ã«ã«éå®ãããŠããããããã³ãããçææ¡ä»¶ã«ãã£ãŠåºåã«åŸ®åŠãªå·®ç°ãçããããšããããŸãã
v8
èçæŽæ°ïŒä»¥äžã®ã¿ã°ã®åŠç¿ã匷åããŸããïŒ
Texture Update: 以äžã®ã¿ã°ããã¬ãŒãã³ã°ã§åŒ·åãããŸããïŒ
realistic, photorealistic, flat color,shiny skin, matte skin, shiny hair,danbooruããŒã¿ã»ããã«ã¯ãåçãããåçã«è¿ãã¹ã¿ã€ã«ãã衚ãã¿ã°ã倿°ãããŸããç§ã¯ãã¬ãŒãã³ã°ã»ããå ã§ãããã®ç»åã«çµ±äžããŠãphotorealisticããšã¿ã°ä»ãããŸããããããdanbooruãã¬ãŒãã³ã°ã»ããã§åŠç¿ããSDXLã¢ãã«ã®å€ãã¯åå®çãªç»åãããŸãæãããšãã§ããªãããããphotorealisticãã¯äœãéã¿ã§äœ¿ãããšãæšå¥šããŸããèçã®èª¿æŽã«ã¯é©ããŠããŸããå宿§ãåµåºããã«ã¯åããŸããããrealisticãã¯é«ãéã¿ã§æ£åžžã«æ©èœããŸãã
Please note that Danbooru dataset contains multiple tags to describe "photo" or "photo-like styles". Iâve tagged all such images as âphotorealisticâ in dataset.
However, most SDXL models trained on the Danbooru dataset do not render realistic images well. âphotorealisticâ is only recommended at low weight, where it can help adjust texture rather than create realism images. The ârealisticâ tag can work properly at higher weight.
å¿«éäžæ | Quick Start
ããã¯äœã§ããïŒ | What is this?
Pony: People's Works ïŒppwïŒã¯å®éšçãªåŸ®èª¿æŽã¢ãã«ã·ãªãŒãºã§ãããŒã¿ã»ããã®çŽ85%ã¯CivitAIäžã®ãŠãŒã¶ãŒãæçš¿ããAIçæç»åããåéãããŠããŸããåæã®ppwã®ããŒã¿ã»ããã¯pony v6ãçæããç»åãåºã«ããŠãããããæ¬ã·ãªãŒãºã®ã¢ãã«çæç»åã¯pony diffusionã®ç¹åŸŽãä¿æããŠããŸãã
æ¬ã·ãªãŒãºã®ã¢ãã«ã¯æšæºã®Danbooruã¿ã°ã䜿çšããäž»ã«äžãè¿æ¯ã®ã¹ã¿ã€ã©ã€ãºãããŒãã¬ãŒãçæã«åªããŠããŸãããã®ã¢ãã«ã®äž»ãªå¹æã¯ãç»åž«ã¿ã°ã䜿ãããå°ãªãå質ããã³ããã§æ¯èŒçå®å®ããç»åå質ãåŸãããšãã§ããããã³ããã®ããŒã¯ã³ã¹ããŒã¹ãç¯çŽã§ããç¹ã§ãã
æ¬ã¢ãã«ã¯ã¹ã¿ã€ã«LoRAã§ã¯ãªããç°ãªãããã³ãããçææ¡ä»¶ã«ãã£ãŠåŸ®åŠãªç»é¢šã®å·®ç°ãçããå ŽåããããŸãã
Pony: People's Works (ppw) is a experimental fine-tuned model series, approximately 85% of the dataset comes from AI-generated images published by users on CivitAI. Since the earlier ppw dataset was built on images generated by Pony V6, the outputs of this series also carry some characteristics of Pony Diffusion.
This series uses standard Danbooru tags and is mainly optimized for generating stylized portraits at medium and close range. The primary effect of this model series is to allow the basemodel to achieve relatively stable image quality, without artist keywords or long quality tags, freeing up token space for prompts.
These models are not style LoRAs. There may be subtle stylistic variations depending on different prompts and generating conditions.
ããŒãžã§ã³æ å ± | Version Info.
ããã§é åžããŠããã®ã¯ppwã®é«æ¬¡å LoConããŒãžã§ã³ã§ããããã®ãããžã§ã¯ãã®ã¡ã€ã³ããŒãžã§ããããŸãã
LoConçppwã¯åçš®æ©èœLoRAãããŒã¹ã¢ãã«ãšæè»ã«çµã¿åããå¯èœã§ã广ã®åŒ·åºŠèª¿æŽãããé«ãå¶åŸ¡æ§ãæã¡ãŸãã髿¬¡å ããŒãžã§ã³ã¯ãã匷åãªæ±åæ§èœãšçŽ°éšæååãæã€åé¢ãã¹ãã¬ãŒãžãšèšç®è³æºãå€ãæ¶è²»ããŸãã
äž»ã«ãªã³ã©ã€ã³çæãµãŒãã¹ã髿§èœPCãŠãŒã¶ãŒã®ããŒã«ã«ç°å¢çšãšããŠèšèšãããŠããŸãã
This page features the high dim LoCon version models of ppw, which also serves as the main page of this project.
The LoCon versions of ppw can be flexibly combined with various functional LoRAs and checkpoints, offering greater controllability over effect weight. High dimension versions provide stronger generalization and more detailed rendering, but it requires more storage space and computational resources.
They are mainly intended for online generation services and local use by users with high-performance PCs.
軜éçLoCon | Lightweight LoCon ver.
ããŒã¹ã¢ãã«ç | Checkpoint versions (Illustrious)
ããŒã¹ã¢ãã«ç | Checkpoint versions (NoobAI)
äœ¿ãæ¹ | Usage
ããžãã£ãããã³ãã:
masterpiece, best quality, very aestheticãã¬ãã£ãããã³ãã:
low quality, displeasingæŽæ°å±¥æŽ | Change log
v7
v7ããŒãžã§ã³ã¯ããŒã¿ã»ããæ§é ãå€§å¹ ã«èª¿æŽããç°ãªããã¬ãŒãã³ã°ãã©ã¡ãŒã¿ãšæŠç¥ã䜿çšããããã以åã®ããŒãžã§ã³ããå®å®æ§ãå£ãå¯èœæ§ããããŸãã
The 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.
v-predã¢ãã«ã¯CivitAIã®ãªã³ã©ã€ã³çæåšãšTensorArtã®ãªã³ã©ã€ã³çæã§åäœãå šãç°ãªããåããã©ã¡ãŒã¿ã§åçŸã§ããŸãããçç±ã¯äžæã§ãâŠâŠ
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...
TensorArtç åãã©ã¡ãŒã¿ã§ã®CivitAIç ããé«ããŠã§ã€ãã§ã®CivitAIç
v7ããŒãžã§ã³æŠèŠïŒ
ããã¯åäœã®ããŒã¿ã»ãããåºã«éçºãããç»åå質åäžLoConã§ãããŒã¿ã®çŽ90%ã95%ã¯CivitAIã®æçš¿ç»åã§ãã
ç»åž«ã¿ã°ã䜿ãããå質ããã³ãããå°ãªãããŠçžå¯Ÿçã«å®å®ããç»åå質ãåŸãããããå€ãã®ããŒã¯ã³ã¹ããŒã¹ãç¯çŽããŸãããŸããã¢ãã«ã®äžéšåºæã®çææ¬ é¥ãä¿®æ£å¯èœã§ãïŒãã ãæã¯é€ãïŒã
ããŒã¿ã»ããã®ç¹æ§ã«ãããçæç»åã«Ponyã®è³ªæãçŸããŸãããç¹å®ã®ç»åž«ãã¹ã¿ã€ã«ãæç»ææ³ãæåããŠããªããããç°ãªãããã³ãããæ¡ä»¶ã§åŸ®åŠã«ç»é¢šãå€ããããšããããŸãã
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.
ããŒã¿ã»ããã®åºå žãšã©ã€ã»ã³ã¹ | Dataset Source & License
ããŒã¿ã»ããå ã®ãã¹ãŠã®ç»åã¯äœè æ¬äººãæäœæ¥ã§éžå¥ãåé¡ã泚éç·šéããŠãããæ°çŸæã¯æç·šéã»ä¿®æ£ãããŠããŸãã
ãã®ã¢ãã«ã¯ç¡æã®ãªãŒãã³ãœãŒã¹ã¢ãã«ã§ããããŠãŒã¶ãŒã¯èªåã®ããã€ã¹ã§èªç±ã«å±éå¯èœã§ããäœè ã¯ã¢ãã«è²©å£²ããå ±é ¬ãåŸãŠããŸãããæ¬ã·ãªãŒãºã¢ãã«ã®åçšçæãµãŒãã¹ãåçšå©çšã®ããã®ç»åçæå©çšã¯äœè ããã®å¶éã¯ãããŸãããã䜵çšããCheckpointãLoRAã®ã©ã€ã»ã³ã¹å¶éã«ã¯æ³šæããŠãã ããã
ããŒã¿ã®çŽ90%-95%ã¯AIçæç»åã§ãããçŽ250æä»¥äžã¯ãããªãã¯ã¡ãã£ã¢ããã¥ãŒã¹ãåºçç©ããéããçŽ æã§æŠå¿µè£å®ãè¡ã£ãŠããŸããä»åŸã®ããŒãžã§ã³ã§ãããã¯åŸã ã«çœ®ãæããããŸããåçšå©çšäºå®ã®ãŠãŒã¶ãŒã¯é¢é£ãªã¹ã¯ã«ã泚æãã ããã
ãã®ããŒã¿ã»ããã«ã¯åå¥ã®ç»åž«ã®èšç·ŽããŒã¿ã¯å«ãŸããŠããããç»åž«æ å ±ã®æ³šéããããŸããïŒAIã«ãã誀ã¿ã°ä»ãã¯å®å šã«ã¯æé€ã§ããŸããïŒã
ãŸããæ¬ã¢ãã«ã®éæºåçšå©çšãã¢ãã«ã®è»¢å£²ãéæºåçšã¢ãã«ãžã®ããŒãžã¯çŠæ¢ãããŠããŸãããªãŒãã³ãœãŒã¹ã®èåã¢ãã«ã®çæãµãŒãã¹å©çšã«ã¯å¶éã¯ãããŸããããèåã¢ãã«ã®åºå žè¡šç€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





