Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
RLe210.safetensors
24 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<av5-stabilizer>
About This Model
STABLE DIFFUSION 1.5 · LoRAs
Created by
Asakura_7724
on Civitai
Creator notes
Please use to load this model ! 请使用 来加载本模型！ Introduction 简介 Q0: What is this model? 这个模型是什么？ A0: 🎈 This is a stabilizer trained for . 这是一个为 训练的“稳定器”。 Q1: What's the use of this model? 这个模型有什么用？ A1.1: 🎉 This model can to some extent fix the collapsed structure in the generated illustration. 该模型能够一定程度上修复画面的崩坏部分。 A1.2: 🎨 This model can fix the pupils of the generated characters. 该模型能够修复生成人物的瞳孔。 A1.3: 😎 This model modifies the lightning effects of the generated illustrations, so that they will be less look like generated by AI (i.e., prefered by human). 该模型会调整生成画像的光影效果，使之看起来“没那么像是AI生成的” （换言之，被人类偏好）。 A1.4: 🍡 This model seems to better align the generated image with the input prompts. 该模型似乎能够更好地对齐生成的图片与输入的提示词。 Q2: How is this model Trained? 这个模型是如何训练的？ A2.1: 🥰 This model is trained by Reinforcement Learning from Human Feedback (RLHF), which has been widely used in LLMs. 该模型由人类反馈强化学习技术训练，该技术已被广泛应用于微调LLMs。 A2.2: 😏 To be specific, this model is trained by , see . 具体而言，该模型的训练基于方法，详见。 A2.3: 🙄 This model is instructed by a self-trained reward model in the training process, using 4 metrics (likes, collections, AI-generated probability, and views). The reward model is available at . 该模型在训练时由一个自己训练的奖励模型指导，使用 点赞数，收藏数，由AI生成的概率，以及浏览量 四个指标来评价。该奖励模型可以在 找到。 Some Nonsense Crap 一些无关紧要的东西 🧐 Any idea and suggestion is welcomed! 欢迎任提供何想法和建议！🧐 🤗 Welcome to challenge NAI3 with a mortal body. 欢迎各位以凡人之躯挑战NAI3 :) 🤗
1,045 downloads · 135 likes on Civitai
SHA256
083A83ADAE7AAB09BCDA1855E45CE5EFE4A15ACA98CB7D0800B34EDA1C426D96
ModelTrends.ai Model ID
#8575
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a
Steps
35
Guidance
7
Seed
2532351179
Size
3072x1736
Prompt
1girl, long hair, solo, twintails, closed mouth, bangs, holding, ribbon, sitting, hair between eyes, jacket, very long hair, long sleeves, shirt, sky, wide sleeves, thighhighs, skirt, cloud, white shirt, brown eyes, collared shirt, feet out of frame, hair ribbon, looking at viewer, outdoors, black jacket, neck ribbon, pantyhose, open clothes, hair ornament, holding can, can, pleated skirt, red ribbon, virtual youtuber, blue sky, day, open jacket, yellow eyes, brown hair, <lora:hbr-000004:1>
Negative prompt
(low quality, worst quality:1.4), (bad anatomy), (blurry:1.4, lips, teeth)
Settings
Sampler
Euler a
Steps
25
Guidance
7
Seed
2430357893
Size
5376x1518
Prompt
1girl, bandaid, hatsune miku, balloon, solo, heart balloon, closed eyes, shirt, bandaid on face, collared shirt, ring, food, blue hair, heart, sleeveless, profile, long hair, flower, necktie, jewelry, white shirt, open mouth, sleeveless shirt, hair ornament, twintails, wings, heart hair ornament, headphones, fork, blue necktie, yellow flower, candy, cake, bandaid on cheek, headset, feathered wings, white wings, bandaid on hand, bare shoulders, rose, eyelashes, glint, sparkle, hairclip, white flower, star \(symbol\), bangs, smile, wing collar, pink flower, angel wings, happy birthday, fruit, chocolate, upper body, orange flower, blush, shiny ------- [A mystery self-trained style]
Negative prompt
(low quality, worst quality:1.4), (bad anatomy), (blurry:1.4, lips, teeth)
Settings
Sampler
Euler a
Steps
35
Guidance
5.5
Seed
1974068798
Size
512x768
Clip skip
2
Prompt
1girl, long hair, solo, twintails, closed mouth, bangs, holding, ribbon, sitting, hair between eyes, jacket, very long hair, long sleeves, shirt, sky, wide sleeves, thighhighs, skirt, cloud, white shirt, brown eyes, collared shirt, feet out of frame, hair ribbon, looking at viewer, outdoors, black jacket, neck ribbon, pantyhose, open clothes, hair ornament, holding can, can, pleated skirt, red ribbon, virtual youtuber, blue sky, day, open jacket, yellow eyes, brown hair «A Mystery Style»
Negative prompt
(low quality, worst quality:1.4), (bad anatomy), (blurry:1.4, lips, teeth)
Settings
Sampler
Euler a
Steps
25
Guidance
7
Seed
295434010
Size
512x768
Clip skip
2
Prompt
1girl, solo, green eyes, weapon, holding weapon, sword, holding sword, brown hair, holding, looking at viewer, jacket, white shirt, bangs, sailor collar, neckerchief, katana, upper body, shirt, mouth hold, school uniform, hair between eyes, serafuku, long sleeves, water, short hair
Negative prompt
(low quality, worst quality:1.4), (bad anatomy), (blurry:1.4, lips, teeth)
AI Models for Image, Video & Text Generation
av5 stabilizer is a LoRA for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models