yyy1026
4 months ago

songMix

This is a merge model based on IL1.0.

Beautiful, detailed, and deep backgrounds complement the main 2D characters.

In order to allow you to understand the nature of the model, the example models are created with the minimum number of prompts.

It responds well to a large number of prompts, so be sure to use this model to create your "best shot."

Steps : 25~40

CFG scale : 3.5~6

Sampler : Euler a

Schedule type : Automatic

Output size : 1536x1536, 1344x1792, 1280x1856, etc.

Quality tags :

masterpiece, best quality, amazing quality, very aesthetic, absurdres, highres, newest,

Negative tags :

negativeXL_D, NEGATIVE_HANDS, average quality, bad quality, worst quality,

Update history

[v1.0] Feb 23, 2025

Merged with the concept of "beautiful background model".

[v1.2] Feb 24, 2025

Compared to v1.0, the character contours have been emphasized to create a more anime-like style.

[v1.3] Feb 28, 2025 <NEW>

We have made it possible to depict characters more softly without compromising the detailed backgrounds of v1.0.

This is an adjustment in the opposite direction to v1.2, so please use it according to your preference.

[v1.01] Feb 28, 2025 <NEW>

This model was made during the development of v1.3. Since it is similar to v1.0, we did not use it in v1.3, but decided to keep it as a successor model to v1.0.

This is the most convenient model for everyday use.

Thank you.

これはIL1.0をベースとしたマージモデルです。

美しく、精細で、奥行きのある背景が、主役となる2Dキャラクターを引き立てます。

モデルの素性を知ってもらうために、作例は必要最小限のプロンプトで作っています。

多量のプロンプトとの反応も良好ですので、このモデルを使ってぜひあなたの"最高の1枚"を生み出してください。

推奨設定

Steps : 25~40

CFG scale : 3.5~6

Sampler : Euler a

Schedule type : Automatic

出力サイズ : 1536x1536, 1344x1792, 1280x1856, 等

クオリティタグ :

masterpiece, best quality, amazing quality, very aesthetic, absurdres, highres, newest,

ネガティブタグ :

negativeXL_D, NEGATIVE_HANDS, average quality, bad quality, worst quality,

更新履歴

v1.0 25/2/23

"美しい背景のモデル"をコンセプトにマージしました。

v1.2 25/2/24

v1.0よりもキャラクターの輪郭を強調してよりアニメ寄りの画風に仕上げました。

v1.3 25/2/28

v1.0の背景の描きこみを損なわずにキャラクターをよりソフトに描写出来るようにしました。

v1.2と反対方向の調整ですのでお好みに応じて使い分けて下さい。

v1.01 25/2/28

v1.3の制作中に出来たモデルです。v1.0と近似しているためv1.3としては使いませんでしたが、v1.0の後継モデルとして残すことにしました。

常用に一番使い勝手のいいモデルです

以上よろしくお願いします。

Read more...

What is songMix?

songMix is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user yyy1026. Derived from the powerful Stable Diffusion (Illustrious) model, songMix 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 songMix is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as base model.

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

Can I download songMix?

Yes! You can download the latest version of songMix from here.

How to use songMix?

To use songMix, 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 songMix, check out our crash course in AI image generation.

Download (6.31 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

1k ~10

Info

Base model: Illustrious

Latest version (v3.2): 1 File

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

12 Versions

😥 There are no songMix v3.2 prompts yet!

Go ahead and upload yours!

No results

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