Liangyi - Hyper-realistic Children's Photography - Fantastic Large Models

0
0
0
0
RealisticPortrait PhotographyGirlBoyPhysical/Facial feature
最近更新:初回公開:
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info
Realistic,Portrait Photography,Girl,Checkpoint,SD 1.5Image info


Children and infants can trigger at different ages, accompanied by the cue word baby or age.

After all, the training set scenes are large, and the proportion of characters is small.

Recommended to use edge, line art, depth, posture, and other methods to control the proportion of characters in the image, ensuring characters do not appear distorted.

For business, customization, and authorization, please contact QQ: 529293436.

Recommended number of steps: 30, 512*768 size

Recommended image size not to exceed 1024; you can enhance resolution through HD restoration.

Recommended to use DPM series samplers, with a sampling step of 30 or more.

Must: HD magnification

Recommended sampling: DPM++ 2M, Karras 3M both optimal

Steps: 20-30  cfg: 4-7

Essential! HD restoration:

Recommended magnification algorithm: 4x-UltraSharp 2x, redraw magnitude 0.2

or 8R-ESRGAN 4x+ Anime6B 2x, redraw magnitude 0.2

After Detailer

<Note>

There is a chance of problems with hands, body, and limbs when generated, may require multiple draws!

- When the character is full-body or small in proportion, there may be distortion or blur in the face. Please enable ADetailer and select face_yolov8n for restoration!

- Some cue words might not show significant effects, future versions will expand their versatility;

——————————————————————————————————

Model Usage Statement:

1. You are not allowed to host this model and its derivative versions (like fusion model versions) on websites/apps intended for earning income or donations. If you intend to use this model and its derivatives for commercial purposes (e.g., generative services, selling images, publishing images on short video platforms, or publications), please contact the creator through internal means;

2. You may not directly sell images generated by this model unless you have made sufficient manual modifications to the images, making them legally defined as your personal work. If you violate this clause, you bear all legal consequences personally, and the creator shall not be held responsible;

3. You must not use the model to create or share illegal or harmful content intentionally. Please observe ethical standards and use this model for positive purposes.

4. For Lib release only, no reposting allowed.

ディスカッション

最も人気
|
最新
送信
もうすぐです
ダウンロード
(0.00KB)
詳細
タイプ
オンライン生成回数
0
ダウンロード
0
推奨パラメータ
Sampler method
CFG
7
VAE
なし

ギャラリー

最も人気
|
最新