OneRing
Сombined model of the 90s and 80s and now 00s
Use this model 4th tail (anime/hentai) (Trained on this model and works best with it)
NEW ERA 4.0 (ILLUSTRIOUS-XL) / SDXL / LORA
NEW ERA v1.0 (SDXL / PONY DIFFUSION version combining almost all my popular models with an emphasis on retro anime)
P.P.S. new model Anime Screencap / LORA / PONY DIFFUSION and NEW ERA 3.0 (MODEL) PONY DIFFUSION / SDXL on Boosty
I made a video on how to achieve the same quality or just repeat my art
Do not spam with negative prompts, I selected the minimum amount, which improves the quality, but has almost no effect on the brightness of the image:
Negative prompt: worst quality, low quality, bad hands, fewer digits, extra digits, bad anatomy, english text, engrish text
retro artstyle - main retro token, present in almost all trained images and produces different results from the 80s-90s
1990s \(style\)- a very strong token that significantly changes the style of the model
1980s \(style\)- currently about the same as the previous one (the reason is that the style of the nineties is a lot of the early nineties, and the early nineties are like the eighties)
2000s \(style\)- again it doesn’t work perfectly, but it’s slightly closer to 00s
anime screencap, anime coloring - two strong tokens, works great, makes the image look like screencaps from anime, can be used both together to enhance it, and separately
artists:
by urushihara satoshi
by danmakuman
by kitazume hiroyuki
by kawarajima kou
by kotobuki tsukasa
by hirano toshihiro
new
by mikimoto haruhiko
by kajishima masaki
by saotome nanda
by hakumai gen
P.S. 7.9V (based on 1.5)
Use on Civitai generation service - the checkbox is checked, for some reason it doesn’t work
CFG Scale - 2.5-4 (it's very important guys, I noticed many people use 7 by default, they don't need it, then on 2.5 the image turns out juicy, no more is needed. In addition, the hands and proportions are obtained better by 2.5-3 and the characters do not look like "overcooked chickens")
Please post your work with or without comments, it will help me improve. Thanks!
If you like my work, click on the heart above, I will be pleased :3
What is NEW ERA (New Esthetic Retro Anime)?
NEW ERA (New Esthetic Retro Anime) is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user OneRing. Derived from the powerful Stable Diffusion (SD 1.5) model, NEW ERA (New Esthetic Retro Anime) has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that NEW ERA (New Esthetic Retro Anime) is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, vintage, sexy.
With a rating of 0 and over 0 ratings, NEW ERA (New Esthetic Retro Anime) is a popular choice among users for generating high-quality images from text prompts.
Can I download NEW ERA (New Esthetic Retro Anime)?
Yes! You can download the latest version of NEW ERA (New Esthetic Retro Anime) from here.
How to use NEW ERA (New Esthetic Retro Anime)?
To use NEW ERA (New Esthetic Retro Anime), download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like NEW ERA (New Esthetic Retro Anime), check out our crash course in AI image generation.
Popularity
Info
Latest version (NEW_ERAv5.0(NAI-epsilon)): 1 File
About this version: NEW_ERAv5.0(NAI-epsilon)
NAI-XL Foundation: The new model is based on NAI-XL, marking a significant quality leap compared to the previous model.
Enhanced Detailing: Improved detailing is evident in the environment, eyes, and overall visual elements.
Better Anatomy: There's notable improvement in anatomical accuracy, including better rendering of fingers.
Variety in Clothing: The model offers a broader range of clothing options which increases overall diversity.
Reduced Contrast: Contrast has been lowered; where version 3.0 required a cfg scale of 2.5, the new model achieves similar contrast at a cfg scale of around 4, allowing for additional LORA use.
Improved Scaling: When using Latent (nearest-exact) scaling, there are far fewer artifacts, with anatomy more consistently preserved within correct limits.
11 Versions
Go ahead and upload yours!
