ponyxl_loras_n_stuff.md · hhks/PonyXL_Notes_Backup at 099ff61b13922ea88faf36a318b22bc2e3fe059c

#PonyXL Notes ##Get PonyXL here https://civitai.com/models/257749?modelVersionId=290640

Anons have been experimenting with merging PonyXL with other checkpoints, the following autism mixes have been popular, the DPO one has a much better default style out of the box, PonyXL LoRAs do still work on them but they may have a reduced strength.

https://civitai.com/models/288584?modelVersionId=324619

##List of Ponyxl LoRAs from /h/ NEW NOTE 1/24/2024: I've noticed that some LoRA bakers are using different negatives when testing their LoRAs, which can lead to discrepancies when using them. I've mostly noticed that some LoRAs have a significantly reduced effect if you don't have source_pony or some combination of the source_* tags other than source anime in the negatives. This is unfortunate but a byproduct of not having a standardized process for creating the LoRAs. There's another section down below that has more info about similar issues with PonyXL that's worth reading.

I made a powershell script to try and pull down the LoRAs on this rentry, it will store the last downloaded url for a lora in a history file in case a new or improved one replaces it so you can reuse the script without downloading everything again. You call the script and pass in a destination folder to store the LoRAs. Obviously run at your own risk, I can't prove to you I'm not an asshole or terrible programmer. You'll probably get throttled if you download everything in one go so run it overnight or something. Some of these LoRAs are huge, the whole folder with them all downloaded is ~15 gb.

UPDATE 1/21/2024 I added a basic management interface so it doesn't just pull down everything. You can pick and choose which loras you want. UPDATE 1/22/2024 Added some logic to keep old versions of LoRAs around in case one is updated but you still want to keep the old version around as well.

https://files.catbox.moe/2kiajb.ps1

###Random https://files.catbox.moe/kwo8w4.safetensors sayo_no_uta a horror game from 2003, you would have to look at the lora metadata to know what to prompt, there's flesh on the walls and stuff, fun to mess with https://files.catbox.moe/d9k7nf.safetensors slay_the_princess a visual novel that came out last year that has a sketchy art style, supports 5 of the game's characters: adversary, specter, nightmare, tower, and witch you have to prompt for their features to get them to show up, this file has the characters with their associated tags: https://files.catbox.moe/uprfne.txt, here's some example gens: https://files.catbox.moe/32eskz.png, https://files.catbox.moe/c87hl7.png, https://files.catbox.moe/kp5hbk.png, https://files.catbox.moe/jta8v1.png, https://files.catbox.moe/jsz1rp.png

###Artists These don't require activation triggers unless otherwise stated. Some of these had been previously uploaded to litterbox because they were too large for catbox. Unfortunately the links have expired, I've replaced them with resized versions that are just a couple ranks smaller so hopefully there's no quality loss. These replacement LoRAs have resized on the end of their names. I removed the original ones so people who were lucky enough to download them won't have them overwritten.

###Characters

https://files.catbox.moe/1wdl00.safetensors character_momoka helps to prompt features like hair, clothes https://files.catbox.moe/f5ssgz.safetensors character_tachibana_arisu helps to prompt features like hair, clothes https://files.catbox.moe/9zcayd.safetensors character_matoba_risa helps to prompt features like hair, clothes https://files.catbox.moe/djnlks.safetensors character_amy_sorel example prompt image here: https://files.catbox.moe/qymyf8.png, trigger is amy sorel, outfits are tagged as sc4 and sc6 https://files.catbox.moe/xow8kx.safetensors character_maryjane Prompt is maryjane, though it works better if you prompt for other stuff as well. gradient hair, tentacle hair, head fins, fangs, long tongue, etc https://files.catbox.moe/ccbfrs.safetensors character_neopolitan_rwby activation seems to be neo_politan, example gen: https://files.catbox.moe/m77z3a.png https://files.catbox.moe/0fmlta.safetensors character_naoto_shirogane looks like Shirogane Naoto is the activation trigger, example prompt image: https://files.catbox.moe/hf88vs.png https://files.catbox.moe/vsky78.safetensors character_shinobu_jackobs example prompt image: https://files.catbox.moe/jale97.png, activation trigger is shinobu jackobs https://files.catbox.moe/z8j9aq.safetensors character_roll_exe https://files.catbox.moe/ifr6a5.safetensors character_mayl_sakurai activation trigger is maylsakurai, can also prompt for the following 'blue vest', 'green sleeves', 'pink skirt', 'black thighhighs', 'hair ornament' https://files.catbox.moe/e9ult9.safetensors character_scarlet_ff7 activation trigger is scarlet_(ff7), also helps to prompt asymmetrical hair, blonde_hair, red dress if you want her in her typical red dress, looks best with 3d in the prompt due to the limited amount of images out there, once you put 3d in the negatives it starts to look a lot less like her https://files.catbox.moe/mxnwc6.safetensors character_fern https://files.catbox.moe/qxdzd4.safetensors character_luna_platz outfit infers very well as long as it isn't manipulated too much, you might see issues with things like dress/skirt lift. This LoRA is very flexible with other outfits known by your base model. Main activation token: lunaplatz Outfit: long-sleeve dress, lapel pin, striped pantyhose Optional: blue pantyhose https://files.catbox.moe/zrudlt.safetensors character_harp_note has a complicated outfit, so for full control over what is inferred by the model, there are very unique tags, and in all be pretty lengthy, especially for ponyxl. Main activation token: harpnote Outfit: helmet, tinted eyewear, pink dress, pink dress straps, bodysuit under clothes, striped detached sleeves, gold bracelet, scarf, pink kneeboots You don't need all of these tokens to infer her nsfw, usually the activation token with 'helmet' and 'tinted eyewear' is enough. https://files.catbox.moe/j7p2f3.safetensors character_ame-chan Trigger token is ame-chan https://files.catbox.moe/h3udxn.safetensors character_neptune Trigger token is smolneptune Outfit: hooded jacket, white choker, d-pad hair ornaments, blue striped thighhighs, blue striped panties Can also closely replicate her frilled swimsuit with 'orange frilled bikini'.

##Innate artists/styles List of tags innate to ponyxl that change the style significantly, usually artists but sometimes other strange behavior some of these could just be getting activated by character names in the artist name or just misfires in the AI network ¯_(ツ)_/¯

asura (asurauser) mirai hikari cutesexyrobutts bb (baalbuddy) (questionable quality) dd (ijigendd) (not sure if it actually matches the real artist) hara (harayutaka) hews boris (noborhys) m-da s-tarou tsukishiro_saika tsukudani_(coke-buta) (strange behavior with hair) agawa_ryou (seems pretty faithful but lips are always really full) sumiyao (amam) neocoill tomose shunsaku, null (nyanpyoun), horosuke chanta (ayatakaoisii), (hard to tell if it's faithful) merunyaa (seems to be the character not really the style) fumihiko (fu mihi ko) (always drenched in sweat for some reason) aaaa (quad-a) (I like this one!) cle masahiro (everything has rim lighting) kasumi (skchkko) murakami suigun (not sure if actually the artist, pretty strange eyes) fumio (rsqkr) yomu (sgt epper) homare (fool's art) happoubi jin (seems to be slight? not sure) asamura hiori (doens't seem faithful but looks interesting!) moisture (chichi) (seems faithful) dandon_fuga kase daiki taka (taka wo kukuru) ririko_(zhuoyandesailaer) mo_(kireinamo) akinbo_(hyouka_fuyou) aztodio kaisen_chuui sousouman bee_(deadflow) sano_toshihide mitsumi_misato personal_ami donguri_suzume lambda_(kusowarota) jack_dempa lm_(legoman) minakami_(flyingman555) jellytits-7 amasora_taichi em_(totsuzen_no_hakike) kurokoshou_(emuburemu123) niliu_chahui kawakami_rokkaku miyase_mahiro momo_no_sukebe minato_ojitan joy_ride osiimi mosho fuya_(tempupupu) jabara_tornado konno_tohiro 23_(real_xxiii) kashu_(hizake) mizuryu_kei kairunoburogu mizuumi_(bb) nagase_haruhito nottytiffy akashio_(loli_ace) liang_xing vahn_yourdoom nakamura_regura aster_crowley cian_yo hekiga_(freelot) tsukiyo_(skymint) nyong_nyong tony_guisado tebi_(tbd11) neoartcore yoi_naosuke damao_yu masami_chie

from here will try to classify them better, too lazy to revisit past ones strong and accurate (may need strength tweaking) tony_taka dross hua-j sparrow firolian paloma_piquet akano_murasaki Kawamoto Toshihiro blade_(galaxist) bittenhard stealth-brock, (also maybe shenanimation, alt) incase sunna (nilsunna) wagashi (dagashiya) sagiri melkor_mancin alp elf (stroll_in_the_woods) tomu (tomubobu) kame (kamepan44231) cyancapsule kelvin hiu neisan pija (pianiishimo),

strong and doesn't look anything like the artist imo but still possibly useful through varying strength and combining with other artists kelvin-trainerk (maybe something to do with kelvin above?) geo_(yukishitadou) fadingz sima_naoteng nyororiso_(muyaa)

seems to induce a change but I could be hallucinating or it could be just due to the randomness of the model

nemunemu_(candy_paddle) kurokaze_no_sora kapuru_0410 iro_ame_(amewaagada) hisakawa_chin sunga2usagi shirokuma_(nankyoku) kokura_masashi hinaki_(hinaki_0102) haru_(hiyori-kohal) hanamasa_ono amano_kozue ziro_(zirorong) shiromoru_(yozakura_rety) sakura_hanpen nyonyonba_tarou miyuki_(miyuki0529) ichirino_minagi shimashiro_itsuki nijihashi_sora mugichoko_(mugi_no_choko) kamimiya haneramu nakamura_rohane oimo_(imoyoukan) mugi_(banban53) mana_kakkowarai

last tried was yanyan_(shinken_gomi)

##Innate Characters An anon went through the trouble of compiling a list of characters known to the model, these are not comprehensive it seems to know hundreds if not thousands of characters. Any popular female character from a popular franchise has a good chance of being known to the model, movies, video games, and tv shows are a good source.

Females: https://files.catbox.moe/oklpz8.txt Males: https://files.catbox.moe/1lptzn.txt Female Pokemon: https://files.catbox.moe/sljtm8.txt Male Pokemon: https://files.catbox.moe/ka331j.txt Western Characters: https://files.catbox.moe/15bayo.txt More Western Characters: https://files.catbox.moe/bhjnpb.txt

##Tricks with the model for more anime style There's some evidence that the model has a bit of a bias towards western style art, particularly when using the score tags (it is made by furries after all). It might be beneficial to tag your image sets with the score tags, the laziest way would be to tag every image with score_9, source_anime, this may affect the overall "quality" of images the lora generates since some of the knowledge in the model about "high quality" might be overwritten but it will look more like the artist's style.

You can also help nudge generations with the model more towards anime style by using "source_cartoon, source_furry, source_pony, sketch, painting, monochrome" in the negative prompt when generating images. Some of the artists with more subtle art styles tend to have more success with this in my experience. The bias is a bit less evident in the lower scores so if a LoRA has it's images tagged with score_9 a prompt like "source_anime, score_9, score_6_up, score_5_up, score_4_up" might get better results. Unfortunately this also makes your LoRA harder to use, you'd have to tell people to use it this way.

Other tricks tried were to include all the score tags in the LoRA's training set on every image which didn't have much success or only using the source_anime tag which also didn't seem to influence the LoRA's effectiveness much. I haven't tried actually using the score tags as intended since that takes more effort than I'm willing to put in for a LoRA for the time being but that may net the best results.

##LoRA Training Update 1/30/2024 I've been messing around with Lycoris locon, which needs inputs for conv network rank and alpha which I generally saw recommendations to set it to the network rank and alpha of the model (and to not exceed 64). Not sure how easy it is to use with the UI frontends but here's what the commandline looks like for kohya-ss. As always any criticism is welcome on /hdg/ I've actually gotten some good feedback on there.

--network_module = networks.lora --train_data_dir = "$IMAGES_PATH$" --output_dir = "$OUTPUT_FOLDER$" --output_name = "$LORA_NAME$" --pretrained_model_name_or_path = "$PATH_TO_PONYXL_CHECKPOINT$" --max_train_epochs = $NUMBER_EPOCHS$ --train_batch_size = 12 --resolution = "1024,1024" --save_every_n_epochs = 1 --save_last_n_epochs = 999 --learning_rate = 1 --lr_scheduler = cosine --lr_warmup_steps = 0 --network_dim = $NETWORK_RANK$ --network_alpha = $NETWORK_ALPHA$ --seed = 1056283418 --keep_tokens = 0 --gradient_checkpointing --max_data_loader_n_workers = 16 --mixed_precision = bf16 --save_precision = bf16 --network_module = lycoris.kohya --network_args "preset = unet-transformer-only" "conv_dim = $NETWORK_RANK$" "conv_alpha = $NETWORK_ALPHA$" "algo = locon" --optimizer_type = "prodigy" --optimizer_args "decouple = True" "weight_decay = 0.01" "d_coef = 0.8" "use_bias_correction = True" "safeguard_warmup = False" "betas = 0.9,0.99" --caption_extension = ".txt" --prior_loss_weight = 1 --cache_latents --cache_latents_to_disk --xformers --save_model_as = safetensors --enable_bucket --min_bucket_reso = 512 --max_bucket_reso = 2048 --bucket_reso_steps = 256

##Old LoRA training settings These are my old LoRA training settings with prodigy, didn't really have any major issues with it, keeping it around for reference.

--network_module = networks.lora --train_data_dir = "$IMAGES_PATH$" --output_dir = "$OUTPUT_FOLDER$" --output_name = "$LORA_NAME$" --pretrained_model_name_or_path = "$PATH_TO_PONYXL_CHECKPOINT$" --max_train_epochs = $NUMBER_EPOCHS$ --train_batch_size = 2 --resolution = "1024,1024" --save_every_n_epochs = 1 --save_last_n_epochs = 999 --learning_rate = 1 --lr_scheduler = cosine --lr_warmup_steps = 0 --network_dim = 64 --seed = 1055217506 --keep_tokens = 0 --gradient_checkpointing --max_data_loader_n_workers = 8 --mixed_precision = bf16 --save_precision = bf16 --optimizer_type = "prodigy" --optimizer_args "decouple = True" "weight_decay = 0.01" "d_coef = 0.8" "use_bias_correction = True" "safeguard_warmup = False" "betas = 0.9,0.99" --caption_extension = ".txt" --prior_loss_weight = 1 --enable_bucket --min_bucket_reso = 512 --max_bucket_reso = 2048 --bucket_reso_steps=256 --xformers --save_model_as = safetensors --cache_latents --cache_latents_to_disk --network_train_unet_only --cache_text_encoder_outputs