Model

V5_SD1.5:模型主要训练胶片摄影、计算摄影、数码原片三大类，对亚洲人像进行深入微调,目前训练集主体为亚洲年轻男性、女性、少量风光,使用GPT4V进行打标，部分使用Cogvqa、WD1.4混合标注，...

SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.Version na...

2023/7/27 updateAdd some comic covers to the dataset. Process the edges of the sketches to remove pixels that are irrelevant to the training content. Retrain the model using ne...

2023/4/17 updateAssign different weights to each tag for training. Adjust linear dim to 64. The preview images of the new model are generated using 'Hires Fix' and upscaled wit...

PLEASE READ - WORKFLOW BELOW:-This will probably be the LAST UPDATE for the Dragonfruit models, for a while, at least until I am happy enough with my realistic merge (currently...

? for Updates - I would love to see your reviews and images of this model, feel free to post them below!Pathfinder branches from Maverick's flexibility fusing in Nu Element and...

text2img使用时注意提示词丰富一点，或者把close-up放到负面，不然容易出牙齿特写,可以用于inpainting，将普通牙变成尖牙，或者只在img2img的正面提示词使用来改变牙齿,2D模型可以得到更长...

Angel's mind in a succubus's body.Datesets not enough, improvement needed.Sleeves might turn black due to the technical problem within SD, as you might have met the situation w...

SDXL LoRA/LyCORIS works best on the model that it was trained on. I will release multiple versions for a few popular models. Feel free to request for artist or model.Version na...

Japanese interior design, also known as "Wa" or "Nihon" style, is a distinct and highly regarded aesthetic that reflects the cultural and traditional elements of Japan. ...

Models version befor Soles Toy is not recommand. I suggest to use negtive embedding an12, from asyncforai414, you can find it on Civitai.在Soles Toy之前的版本模型都不推荐,我建...

LoRA XL Models - CivitAI Repository ?Welcome to the FFusion LoRA extracted models repository on Hugging Face & CivitAI! Here, we present a collection of models extracted us...

针对SD画不好武术做的强化训练，例图为用2次元画底图在用写实模型来强化细节（不会的可以去看我的B站教程）直出图可以看我返图区例图，直接用写实可能构图没有2次元好采样器：画底图推荐DDI...

V1.1 changelog:train on 1.0 new dataset to integrate new linguistic depth and to add detail and precisionknown issues: from version 1 onwards there are problems with hands and ...

POLTERGEIST MIXComic/Illustration styled model that inspired Osenayan Mix Illustration. Due to the way it's created it is consistently trained and re-trained via loras (lora fu...

(日本語説明は後半にあります)Reproduces sensual (seductive, voluptuous) face with half-closed (and a bit wet) eyes and inverted-v-shaped eyebrows. Also suitable for smirking fac...

If you like what I do, leave me a ❤️ to receive notifications of future updates and follow me here on Civitai. Remember that it is a hobby for me and it costs a lot of time and...

Update 2:ReV_3 released. Read model version description for more infoUpdateReV_2 released. Read model version description for more infoIntroThis model is mainly intended for Po...

Style LyCORIS of artist MARE.More accurate with negative: '3d' 描述: Trained on ponydiffusionXL V6 训练词语: ...

Commission and Exclusive LoRA, Visit my BMC page(Please try my newest Negative Prompts! I think it helps alot to generate a better image :)(EXPERIMENTAL .Ver)WARNING! "NSFW pro...