aueki4g467
10 months ago

Beyond01c

Beyond is a name that indicates that the goal is to exceed the expressiveness of SD1.5. One of the prototypes has already been released as 00, but there are more than 10 versions before and after that that are completely different from the base. The common problem is that the body structure, especially the fingers, is unstable. The same is true for 01c this time, and although the rate of broken images is high, it is still relatively better. Since it is an LCM model, please make a number of images to find good ones. I don't use negative prompts, so I don't know, but it may be possible to avoid this to some extent by using appropriate embedding.

BeyondはSD1.5の表現力を超えることを目標にすることを示す名前です。すでに試作段階のものの1つを00として公開していますが,その前後のバージョンで,ベースから全く異なっているものだけでも10種以上はあります。手指を代表とする身体構造が安定しないというのが共通した問題点です。今回の01cも同様で,壊れた絵の出る率は高めですがまだ比較的マシな部類です。LCMモデルですので,数を出してよい絵を探してください。私はネガティブプロンプトは使用しない人なのでわかりませんが,適切なEmbeddingを使えばある程度回避できるのかもしれません。

------------------------------------

Beyond00R

The test version released earlier was the one used in the test to reproduce the LoRA sample. However, there were some points of dissatisfaction, so I kept it unreleased. However, when I tried to resolve those points of dissatisfaction, another problem arose and I was thinking of changing my approach a little. The version used in the sample is not the finished product of this branch, so I will release a slightly refined version. There is not a big difference, but I think the balance of details is better. To be specific, there is a little more detail than before, and the drawing has been improved a little.

The material and stitching of the clothes are quite realistic, but this is the realism of a cosplay costume, and it may be a little different for a fantasy model. Well, it probably won't look good even if I reproduce realistic leather armor.

先に公開したテスト版は,LoRAのサンプルを再現するためにテストで使ったものをそのまま公開しました。しかし,それはいくつか不満点が残るものだったので未公開にしていたものだったわけですが,その不満点を解消しようとすると別の問題が出てきて少し方針転換を考えていたところでした。サンプルで使ったバージョンが,このブランチでの完成品というわけでもありませんので少しリファインしたものを公開しておきます。さほど大きな違いがあるわけではありませんが,ディテールのバランスがよりよいものになっていると思います。具体的にいうと,前のより少しディテールが多めで,描画も少し改善されています。

服装の材質や縫製などはかなりリアルになっていますが,これはコスプレ衣装のリアルさであって,ファンタジーモデルとしては少し方向が違うのかもしれません。まあリアルなレザーアーマーなどを再現しても見栄えはしないのでしょうが。

------------------

This is one of the in-progress versions of a fantasy realistic model. I'm releasing the version I used for the sample output in LoRA the other day.

I created LoRA because there was a problem with the coloring of this model, so if you feel the color is bad, try using LoRA in conjunction with it or another solution.

As this is an LCM model, please use LCM for the sampler, 8 for the number of steps, and 2 for the CFG scale as standard.

ファンタジー系リアルモデルの制作途中バージョンの一つです。先日のLoRAでのサンプル出力に使ったものを公開してみます。

このモデルの発色に問題があったのでLoRAを作成したわけですので,色が悪いと感じたらLoRAを併用するかほかのソリューションを試してみてください。

LCMモデルですので,サンプラーにはLCMを,ステップ数は8,CFG scaleは2を基準としてください。

Read more...

What is Beyond-LCM?

Beyond-LCM is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user aueki4g467. Derived from the powerful Stable Diffusion (SD 1.5) model, Beyond-LCM 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 Beyond-LCM is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as photorealistic, base model, sci-fi.

With a rating of 0 and over 0 ratings, Beyond-LCM is a popular choice among users for generating high-quality images from text prompts.

Can I download Beyond-LCM?

Yes! You can download the latest version of Beyond-LCM from here.

How to use Beyond-LCM?

To use Beyond-LCM, 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 Beyond-LCM, check out our crash course in AI image generation.

Download (1.94 GB) Download available on desktop only
You'll need to use a program like A1111 to run this – learn how in our crash course

Popularity

400 ~10

Info

Base model: SD 1.5

Version 00 v1.1R: 1 File

To download these files, please visit this page from a desktop computer.

7 Versions

😥 There are no Beyond-LCM 00 v1.1R prompts yet!

Go ahead and upload yours!

No results

Your query returned no results – please try removing some filters or trying a different term.