update

README-zh.md

@@ -1,159 +0,0 @@
----
-license: creativeml-openrail-m
-tags:
-- Text-to-Image
-- stable-diffusion
-- lora
-language:
-- en
-- zh
----
-
-# Stable Diffusion NAI lora Index
-
-[中文文档]()
-
-
-[lora](https://github.com/cloneofsimo/lora) is one way to fine-tune a stable-diffusion model.
-It can result in a model smaller than a dreambooth model, and provide better result compared with textual inversion outcome(embeddings).
-
-This repo is for indexing LoRA works in huggingface and try to introduce the model in the same format: The idea is to use simple, mandatory and consistent prompts to show the result (similar to benchmark).
-
-As [webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) now support lora, the structure will follow the webui fashion.
-You can simply clone this repository and clone the repositories in the index to use the lora models in your local webui.
-
-Please contact me or create pull request if you find something should be included.
-## YoungMasterFromSect/Trauter_LoRAs
-Link: https://huggingface.co/YoungMasterFromSect/Trauter_LoRAs
-
-The owner is managing his model card quite well. So, I will only copy his index here.
-
-**Genshin Impact**
-
-Eula, Barbara, Diluc, Mona, Rosaria, Yae Miko, Raiden Shogun, Kujou Sara, Shenhe, Yelan, Jean, Lisa, Zhongli, Yoimiya
-
-**Blue Archive**
-
-Rikuhachima Aru, Ichinose Asuna
-
-**Fate Grand Order**
-
-Minamoto-no-Raikou
-
-**Misc. Characters**
-
-Aponia, Reisalin Stout
-
-**Artstyles**
-
-Pozer
-
-## dranzerstar/SD-textual-inversion-embeddings-repo
-
-Link: https://huggingface.co/dranzerstar/SD-textual-inversion-embeddings-repo
-
-## swl-models/sd-concepts-library-lora
-
-Link: https://huggingface.co/swl-models/sd-concepts-library-lora
-
-## ikuseiso/Personal_Lora_collections
-
-Link: https://huggingface.co/ikuseiso/Personal_Lora_collections
-## sylveriate/lora-characters
-
-Link: https://huggingface.co/sylveriate/lora-characters
-
-**abigail**
-
-![abigail](lora-characters-previews/abigail.png)
-
-**emilico**
-
-![emilico](lora-characters-previews/emilico.png)
-
-**hiroikikuri**
-
-![hiroikikuri](lora-characters-previews/hiroikikuri.png)
-
-**kateshadow**
-
-![kateshadow](lora-characters-previews/kateshadow.png)
-
-**pippa**
-
-![pippa](lora-characters-previews/pippa.png)
-
-**selen**
-
-![selen](lora-characters-previews/selen.png)
-
-**shondo**
-
-**shondo-improved**
-
-![shondo](lora-characters-previews/shondo-improved.png)
-
-**tenma**
-
-![tenma](lora-characters-previews/tenma.png)
-
-
-## DONOT KNOW THE SOURCE
-
-These models are in this repo, if you know the source, please contact me. I will change them to the links.
-
-### Genshin Impact
-
-**qiqi**
-
-Trigger token is "qiqi", also "1girl", "solo" are recommended.
-
-``` shell
-# Sample prompts
-1girl, qiqi, jiangshi, qing guanmao, coin hair ornament, ofuda, bead necklace, qiqi \(genshin impact\)
-```
-
-![qiqi](qiqi.png)
-
-**klee**
-
-``` shell
-"1girl, klee"
-"1girl, nsfw, klee, solo, completely nude, hat"
-"1girl, klee, solo, ahoge, hat feather, twintails, gloves, boots, bag, red dress, bangs, backpack, dress, brown gloves, knee boots, low twintails, brown footwear, cabbie hat, red eyes, pointy ears, long sleeves, clover print, scarf, socks, hat, blonde hair, kneehighs, coat, charm \(object\), brown scarf, hair between eyes, red headwear, light brown hair, bag charm, randoseru, sidelocks, hat ornament, bloomers, pocket, red coat, white socks, feathers, white feathers, klee \(genshin impact\)"
-```
-
-![klee](klee.png)
-
-**nahida**
-
-nahida_cross-shaped_pupils_finger_frame
-
-- can do beautiful cross-shaped pupils, but only in close-up/portrait/eye focus pictures
-- was an attempt at finger frame. didn't go well
-Might still be useful for extremely pretty portraits.
-
-![nahida_cross-shaped_pupils_finger_frame](nahida_cross-shaped_pupils_finger_frame.png)
-
-nahida_weighted
-
-nahida_weighted was weighted for higher lewds while still retaining outfit fidelity. just apply standard nsfw tags as needed.
-(and an attempt at higher cross-shaped pupils in full body, but it didn't work)
-
-![nahida_weighted](nahida_weighted.png)
-
-Here is the "benchmark"
-``` shell
-# model
-AbyssOrangeMix2_hard.safetensors
-# Seed
-2367322303
-# Size
-512*728
-# Sampler
-Euler a; Step=30
-# prompt
-masterpiece, best quality, {mandatory}, 1girl, solo <lora:xxx:0~1>
-# negative prompt
-lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts,signature, watermark, username, blurry, artist name, (worst quality, low quality, extra digits) 
-```

README.md

@@ -4,22 +4,19 @@ tags:
 - Text-to-Image
 - stable-diffusion
 - lora
-language:
-- en
-- zh
 ---
 
 # Stable Diffusion NAI lora Index
 
-[中文文档](README-zh.md) ： 还没写
-
 [lora](https://github.com/cloneofsimo/lora) is one efficient way to fine-tune a stable-diffusion model.
 
 It can result in a model smaller than a dreambooth model. And provide better result than a textual inversion outcome(embedding).
 
 **This repo is for indexing NovelAI related LoRA works in huggingface.**
 
-**Preview the "good models" with no "explaination" in their repos using a "benchmark".**
+**Preview the "good models" with no "explaination" in their repos using a benchmark.**
+
+**You may use CTRL+F to find keywords you are interested to quickly get the source.**
 
 Note that NSFW will not be included since I cannot put previews.
 
@@ -50,12 +47,16 @@ Link: https://huggingface.co/dranzerstar/SD-textual-inversion-embeddings-repo
 
 Link: https://huggingface.co/ikuseiso/Personal_Lora_collections
 
+The owner starts to upload his model card, so I will only update the keywords in the future.
+
 Note that the owner claimed that the weight should be set to 0.6~0.8.
 
 So, I take 0.7 for all the previews below.
 
 **models**: ame-chan_needy_girl_overdose, chouzetsusaikawa_tenshi-chan, grea_shingeki_no_bahamut, iono_pokemon, kisara_engage_kiss, laundry_dragonmaid, lishenna_omen_of_destruction, lovely_labrynth_of_the_silver_castle, lucy_cyberpunk, Miorine_Rembran, ralmia_sonic_racer, seulbi_lee, suletta_mercury, vampy
 
+vergil, devil may cry, ace, sky striker
+
 ![1](ikuseiso/Personal_Lora_collections/1.jpg)
 
 ![2](ikuseiso/Personal_Lora_collections/2.jpg)
@@ -88,10 +89,10 @@ So, I will only copy the Links and summarize keywords.
 Link: https://huggingface.co/YoungMasterFromSect/Trauter_LoRAs
 
 **Genshin Impact**
-: Eula, Barbara, Diluc, Mona, Rosaria, Yae Miko, Raiden Shogun, Kujou Sara, Shenhe, Yelan, Jean, Lisa, Zhongli, Yoimiya
+: Eula, Barbara, Diluc, Mona, Rosaria, Yae Miko, Raiden Shogun, Kujou Sara, Shenhe, Yelan, Jean, Lisa, Zhongli, Yoimiya, Ganyu
 
 **Blue Archive**
-: Rikuhachima Aru, Ichinose Asuna
+: Rikuhachima Aru, Ichinose Asuna, Karin
 
 **Fate Grand Order**
 : Minamoto-no-Raikou
@@ -100,7 +101,7 @@ Link: https://huggingface.co/YoungMasterFromSect/Trauter_LoRAs
 : Aponia, Reisalin Stout
 
 **Artstyles**
-: Pozer
+: Pozer, CuteScrap
 
 Link: https://huggingface.co/breakcore2/loras
 
@@ -118,6 +119,14 @@ Link: https://huggingface.co/Doctor-Shotgun/ds-LoRA
 
 Persona5: Ann Takamaki, Futaba Sakura, Haru Okumura, Kasumi Yoshizawa, Makoto Niijima
 
+Link: https://huggingface.co/V3B4/LoRA
+
+I usually generate black image because of NaN for VAE when using his models.
+
+Maybe caused by OrangeMix and angthing4.5?
+
+osaka_shizuku, hitotsuyanagi_riri, yoshida_yuuko, chiyoda_momo
+
 ## DONOT KNOW THE SOURCE
 
 You can download the models in this repo, if you know the source, please contact me. I will change them to links.