Upload 16 files

models/README/AIイラストおじさん_README.txt

@@ -0,0 +1,14 @@
+AIイラストおじさん - Manual
+link: https://civitai.com/models/481765/ai
+recommend Model:
+
+Pony Diffusion V6 XL
+essential prompts for the style to work properly: shiny, shiny skin, shiny outfit, wet clothes, wet skin<lora:AIイラストおじさん:1.0>, skindentation
+
+Recommended negative prompts: monochrome, greyscale, blurry.
+
+Recommended CFG Scale: 3.0 - 7.0
+
+Recommended sampler: Euler a
+
+This note was posted on 08/15: As you insisted so much, I will soon be launching Version 2.0 of Lora :)

models/README/BSSStylesForPonyRealism_README.txt

@@ -0,0 +1,7 @@
+BSS - Styles for Pony Realism - Manual
+
+link: https://civitai.com/models/623269?modelVersionId=699461
+
+description:
+
+Triggers - NEOST, NEON LIGHTS

models/README/Cutesexyrobutts_README.txt

@@ -0,0 +1,15 @@
+Cutesexyrobutts - Artist Style | Pony - Manual
+
+link: https://civitai.com/models/497878?modelVersionId=746437
+
+Description:
+
+Version 1 is a DoRA, so you'll need need A1111 1.9.0 or newer or apply this PR on your Forge installation.
+
+Artist Style model of artist Cutesexyrobutts. Upon the artist's request I will remove this model.
+
+Please support the artist.
+
+Sample images were generated using DPM++ 2M / DPM++ 2Sa / Restart with a variety of scedulers on AutismMix Confetti. See samples for examples.
+
+Recommend using with base PonyDiffusion or AutismMix.

models/README/D2PonyXL_README.txt

@@ -0,0 +1,17 @@
+D2PonyXL - Manual
+
+link: https://huggingface.co/hhks/PonyXL_Styles_Backup/tree/main/D2PonyXL_v003d-epoch6
+
+Description:
+
+This LORA model is designed to enhance curvy body shapes in anime and analog photo-look backgrounds. It was trained on a dataset of 1782 images for training a+b and 929 images ("best of") for c+d.
+
+Key Features:
+
+    Training: Over 70 hours of training on Prodigy O_o
+    Intended Use: Mix with your prompts for curvy body shapes. Use at <lora:FILENAME:0.66> for anime-look or <lora:FILENAME:0.3:0.8> for realistic results.
+    Settings: Low denoise (0.1-0.2) and recommended resolution: 672x1024 or 1024x672.
+    Trained Look Concepts: Dim lighting, warm colors, bloom, analog photograph, foreshortening.
+    Additional Features: Various trained haircuts, shiny skin, etc. (see tag frequency in metadata).
+    Mandatory Attributes: Large breasts, large areolae, and precise tan.
+    Recommended Checkpoint: Pony Diffusion for Anime.

models/README/DPO_README.txt

@@ -0,0 +1,28 @@
+DPO (Direct Preference Optimization) LoRA for XL and 1.5 - OpenRail++ - Manual
+
+link: https://civitai.com/models/242825/dpo-direct-preference-optimization-lora-for-xl-and-15-openrail
+
+Description:
+
+What is DPO?
+
+DPO is Direct Preference Optimization, the name given to the process whereby a diffusion model is finetuned based on human-chosen images. Meihua Dang et. al. have trained Stable Diffusion 1.5 and Stable Diffusion XL using this method and the Pick-a-Pic v2 Dataset, which can be found at https://huggingface.co/datasets/yuvalkirstain/pickapic_v2, and wrote a paper about it at https://huggingface.co/papers/2311.12908.
+What does it Do?
+
+The trained DPO models have been observed to produce higher quality images than their untuned counterparts, with a significant emphasis on the adherence of the model to your prompt. These LoRA can bring that prompt adherence to other fine-tuned Stable Diffusion models.
+
+Who Trained This?
+
+These LoRA are based on the works of Meihua Dang (https://huggingface.co/mhdang) at
+
+https://huggingface.co/mhdang/dpo-sdxl-text2image-v1 and https://huggingface.co/mhdang/dpo-sd1.5-text2image-v1, licensed under OpenRail++.
+
+How were these LoRA Made?
+
+They were created using Kohya SS by extracting them from other OpenRail++ licensed checkpoints on CivitAI and HuggingFace.
+
+1.5: https://civitai.com/models/240850/sd15-direct-preference-optimization-dpo extracted from https://huggingface.co/fp16-guy/Stable-Diffusion-v1-5_fp16_cleaned/blob/main/sd_1.5.safetensors.
+
+XL: https://civitai.com/models/238319/sd-xl-dpo-finetune-direct-preference-optimization extracted from https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/sd_xl_base_1.0_0.9vae.safetensors
+
+These are also hosted on HuggingFace at https://huggingface.co/benjamin-paine/sd-dpo-offsets/

models/README/DetailEnhancer_README.txt

@@ -0,0 +1,16 @@
+Detail Enhancer (SDXL) - Manual
+
+link: https://civitai.com/models/162967/detail-enhancer-sdxl?modelVersionId=183635
+
+Description:
+
+How to use:
+Use this Lora model in prompt
+
+该模型旨在使SDXL生成的图片具有更多的细节，但请勿使用过高权重，更高的权重意味着更多画面被修改，画风和主体将有可能会受到模型干扰。
+This model aims to add more details to the images generated by SDXL, but please avoid using excessively high weights. Higher weights mean more modification to the visuals, and the artistic style and subject may potentially be affected by model interference.
+Light版本和Heavy版本的区别：
+Light版本对画面的更改要少于Heavy版本，在我们少量的测试中，Heavy版本似乎更擅长把手部四肢等细节画好。
+
+The difference between the Light version and the Heavy version:
+The Light version makes fewer changes to the visuals compared to the Heavy version. In our limited testing, the Heavy version appears to be better at drawing details such as hands and limbs.

models/README/DetailedEyes_XL_README.txt

@@ -0,0 +1,10 @@
+DetailedEyes_XL - Manual
+
+link: https://civitai.com/models/120723/detailedeyesxl
+
+Description:
+
+use 0 images for finetune XLbase, should fit any XL model(even anime)
+add detailed eyes、detailed face and detailed skin
+including neg part and fixed bad hands
+Less effect over 75 tokens

models/README/Doctor Diffusion's Negative XL LoRA_README.txt

@@ -0,0 +1,14 @@
+Doctor Diffusion's Negative XL LoRA - Manual
+
+link: https://civitai.com/models/186617/doctor-diffusions-negative-xl-lora?modelVersionId=209546
+
+more details:
+https://doctordiffusion.com/2023/12/14/what-is-a-negative-lora/
+
+Description:
+
+Increate the quality and amount of details with this negative XL LoRA.
+THIS IS MEANT TO BE USED WITH NEGATIVE STRENGHT VALUES.
+An updated version my "point-e" negative embedding for use with XL.
+Keep CLIP strength at 1.0 and adjust the strength of the LoRA to preference.
+LoRA Strength can range from -0.01 to -2.00.

models/README/FinalFantasyTacticsPony_README.txt

@@ -0,0 +1,12 @@
+Final Fantasy Tactics XL/Pony(Akihiko Yoshida Style) - Manual
+
+link: https://civitai.com/models/158021/final-fantasy-tactics-xlpony-akihiko-yoshida-style
+
+Description:
+
+Final Fantasy Tactics XL - Akihiko Yoshida Style
+
+The intend of this LoRa is to provide a tool to generate your own classes/jobs using the style of Final Fantasy Tactics art by Akihiko Yoshida. This model can also be used to generate fantasy related artwork with some "handmade" feeling to it!
+To create job images use the wording "male/female" and "full body". further descriptions can be added to the prompt, if none provided a random class will be generated. (Adding game art style helps standardize the output).
+The XL models provide a wide variety of already inbuilt classes that you can explore and play with being able to come with very original designs for customized classes that were not originally in the Final Fantasy games.
+The weight of this LoRa varies with models and how intense you want the style (as usual with LoRas), 1.25 seems to work well with me! I provided a lot of examples so you can check the differences!

models/README/HeartFingersConceptLora_README.txt

@@ -0,0 +1,6 @@
+Heart Fingers | Concept Lora - Manual
+link: https://civitai.com/models/400207?modelVersionId=446320
+
+Description:
+
+Activation Tags - heart fingers, heart hands,

models/README/IncaseStyle_README.txt

@@ -0,0 +1,100 @@
+Incase Style [PonyXL] - Manual
+
+link: https://civitai.com/models/300005?modelVersionId=436219
+
+Description:
+
+Version Guide:
+
+V1: Weakest style, but high compatibility, struggles with details at lower resolutions.
+
+V2: Recommended for beginners - Good style, good compatibility, hard to mess up.
+
+V3: Best style/colors, maybe reduced compatibility with some other loras.
+
+Top tag counts:
+
+penis                153  (81%)
+female               144  (76%)
+breasts              117  (62%)
+male                 107  (56%)
+cum                  102  (54%)
+erection             96  (51%)
+nipples              91  (48%)
+oral                 83  (44%)
+1girl                82  (43%)
+fellatio             75  (39%)
+straight             72  (38%)
+areolae              64  (34%)
+sex                  60  (32%)
+balls                55  (29%)
+cum inside           55  (29%)
+nude                 54  (28%)
+large breasts        54  (28%)
+lipstick             54  (28%)
+light-skinned male   53  (28%)
+cum in mouth         50  (26%)
+futanari             49  (26%)
+human                48  (25%)
+blue eyes            46  (24%)
+dark skin            44  (23%)
+pussy                41  (22%)
+blush                41  (22%)
+pubic hair           41  (22%)
+open mouth           40  (21%)
+1boy                 39  (21%)
+black hair           38  (20%)
+saliva               37  (19%)
+big breasts          36  (19%)
+penetration          36  (19%)
+cum on face          36  (19%)
+original             35  (18%)
+tongue out           35  (18%)
+light skin           33  (17%)
+long hair            33  (17%)
+clothing             32  (17%)
+handjob              31  (16%)
+freckles             31  (16%)
+pointy ears          31  (16%)
+tongue               31  (16%)
+glasses              30  (16%)
+thighhighs           30  (16%)
+intersex             30  (16%)
+vaginal penetration  30  (16%)
+cum on breasts       30  (16%)
+testicles            30  (16%)
+2boys                29  (15%)
+blonde hair          29  (15%)
+1futa                28  (15%)
+text                 27  (14%)
+spread legs          27  (14%)
+light-skinned female 27  (14%)
+facial               27  (14%)
+interracial          26  (14%)
+red hair             26  (14%)
+piercing             26  (14%)
+anal                 26  (14%)
+dark-skinned male    26  (14%)
+futa on female       25  (13%)
+earrings             25  (13%)
+gloves               25  (13%)
+orange hair          25  (13%)
+makeup               25  (13%)
+clothed              24  (13%)
+ass                  23  (12%)
+cleavage             23  (12%)
+dickgirl             22  (12%)
+2girls               22  (12%)
+nipple piercing      22  (12%)
+anal sex             22  (12%)
+femboy               22  (12%)
+lipstick on penis    22  (12%)
+humanoid             22  (12%)
+hair                 22  (12%)
+large penis          21  (11%)
+big penis            21  (11%)
+female focus         20  (11%)
+kneeling             20  (11%)
+elf                  19  (10%)
+demon                19  (10%)
+milf                 19  (10%)

models/README/JellyStyle_README.txt

@@ -0,0 +1,13 @@
+Jelly Style - Manual
+
+link: https://civitai.com/models/454586?modelVersionId=550530
+
+Description:
+
+No trigger word required. The end result depends on the base model used, settings, and weight.
+
+Recommended quality tags: score_9, score_8_up, score_7_up, score_6_up. Optional: source_anime
+
+Recommended negative tags: score_4, score_5. Optional: 3d, lips
+
+Recommended checkpoint: AutismMix_confetti

models/README/Petravoice_README.txt

@@ -0,0 +1,9 @@
+Petravoice - Manual
+
+link: https://civitai.com/models/489100/petravoice?modelVersionId=543861
+
+Description:
+
+A LoRA in the style of prompt engineer Petravoice for Pony Diffusion XL.
+recommended strength - 1
+trigger - 1girl, close-up, solo, blurry, chromatic aberration

models/README/ThePitStyle_README.txt

@@ -0,0 +1,91 @@
+ThePit Style [PonyXL] - Manual
+
+link: https://civitai.com/models/305206/thepit-style-ponyxl
+
+Description:
+
+Version Guide:
+
+v1.0 - First base version
+
+v2.0 - Greater versatility, hopefully better style
+
+Top tag counts:
+
+blonde hair             66  (75%)
+female                  62  (70%)
+big breasts             47  (53%)
+1girl                   47  (53%)
+blue eyes               46  (52%)
+huge breasts            43  (49%)
+large breasts           43  (49%)
+female only             38  (43%)
+hourglass figure        38  (43%)
+breasts                 35  (40%)
+busty                   32  (36%)
+long hair               32  (36%)
+makeup                  31  (35%)
+female focus            31  (35%)
+coxville stories        31  (35%)
+wide hips               29  (33%)
+interracial             27  (31%)
+dark skin               27  (31%)
+dark-skinned male       27  (31%)
+bubble butt             26  (30%)
+lipstick                25  (28%)
+solo                    24  (27%)
+high heels              24  (27%)
+earrings                24  (27%)
+tagme                   23  (26%)
+cleavage                22  (25%)
+nipples                 22  (25%)
+male                    21  (24%)
+big penis               21  (24%)
+hoop earrings           20  (23%)
+voluptuous              19  (22%)
+choker                  19  (22%)
+ass                     18  (20%)
+1boy                    18  (20%)
+thick lips              18  (20%)
+muscular female         18  (20%)
+light-skinned female    18  (20%)
+nipple bulge            17  (19%)
+navel                   17  (19%)
+jenny summers           17  (19%)
+tan                     16  (18%)
+erect nipples           16  (18%)
+bimbo lips              15  (17%)
+milf                    15  (17%)
+ponytail                15  (17%)
+huge cock               15  (17%)
+big lips                15  (17%)
+big ass                 15  (17%)
+eyeshadow               14  (16%)
+hoop earrings oversized 14  (16%)
+areolae                 13  (15%)
+light skin              13  (15%)
+muscular                13  (15%)
+full body               13  (15%)
+pink lipstick           13  (15%)
+bracelet                12  (14%)
+athletic                12  (14%)
+muscular male           12  (14%)
+tan body                11  (12%)
+stockings               11  (12%)
+thick thighs            11  (12%)
+2girls                  11  (12%)
+kitty summers           11  (12%)
+standing                11  (12%)
+text                    10  (11%)
+bimbofication           10  (11%)
+the brady bunch         10  (11%)
+veiny penis             10  (11%)
+toned                   10  (11%)
+athletic female         10  (11%)
+toned female            10  (11%)
+looking at viewer       10  (11%)
+eyelashes               10  (11%)
+pinup                   9  (10%)
+penis                   9  (10%)
+nail polish             9  (10%)
+huge ass                9  (10%)

models/README/Vanillaware_README.txt

@@ -0,0 +1,31 @@
+Vanillaware George Kamitani Style PonyXL - Manual
+
+link: https://civitai.com/models/577804/vanillaware-george-kamitani-style-ponyxl?modelVersionId=644333
+
+Description:
+
+This model can only be considered as v0.1, it is not very easy to use normally, and I think it is best to tagging more images in the dataset in detail for better results. In the future, I may slowly complete the training of this model.
+
+The training of this model and the images it generates are solely for learning purposes.
+
+I did nothing, I'm just a porter.
+
+No need for trigger word.
+
+You could find the example prompts from the images above.
+
+Recommended weight: 1~0.6, adjust as needed until the character's appearance meets your requirements.
+
+Upscale value recommendation is around 1.5, denoising strength is 0.2
+
+Looking forward to your comments and images
+
+20240715
+
+The dataset was collected from the works of Vanillaware, including illustrations and game screenshots, mainly focus on the works of George Kamitani.
+
+The performance of this version is not very good, the images it generates may often appear chaotic.
+
+I collected 100+ images as a dataset, but the number is still too much for manual tagging. I initially used wd1.4 to tagging all the images, but the quality of the tagging is still no good, (maybe my usage is not correct enough, and I welcome everyone to make suggestions).
+
+Because I want to see the results quickly, for this dataset, I only manually tagging some images that meet my personal preferences, so the model's output effect will be better for these images.

models/README/Vintage1990sAnimeSDXLLoRAStylePony_README.txt

@@ -0,0 +1,17 @@
+Vintage 1990s Anime SDXL LoRA (Style) Pony - Manual
+
+link: https://civitai.com/models/333041/vintage-1990s-anime-sdxl-lora-style-pony?modelVersionId=373076
+
+Description:
+
+This is a lora I meant to do for a while. It captures the essence of the 90s anime vibe. It also have a touch of vintage parting into it making it more of a retro 90s aesthetic then 100% anime. Like with faded colors and all.
+
+Vintage, 1990s \(style\) add to your prompt for more effect, but you really don't need them.
+
+Best keep under 1 weight, 0.5-0.75 being the sweet spot.
+
+Best for SFW but can also do NSFW
+
+Installation of the LORA:
+
+Copy the safetensors file into the \stable-diffusion-webui\models\lora folder.