Detalhes
Recomendado
v1.0
Photorealism

Photorealism

126.9K
167
385
#Foto
#ferramentas
#photorealism
#ferramenta
#slider

如果你喜歡我的工作可以幫我買杯咖啡,謝謝

If you like what I do, you can buy me a cup of coffee. Thanks.

私の仕事を気に入っていただけたら、コーヒーを一杯おごってください。 ありがとうございます。

https://ko-fi.com/vicentma

This is a reverse version of

Photo-Paint-Slider

Why do this?

  1. Basic theory: Realistic model is better for human body structure, animation model is better for movement and more artistic, I hope to get the advantages of both.

  2. Use the realistic base model as the overall base model, use LORA to adjust the format of the drawing from 3D-PHOTO--->2D-DRAW.

  3. Adjust LORA parameters to find the sweet point.

  4. BothPhoto-Paint-Slider and this better in postive than negtive

V1.0
After understanding the LECO training method, we will adjust the parameters and the learning rate in order to achieve better results with smaller files and less weights.

Available weights are +2~-2, recommended weights are +2~-1.0, positive values provide real tendency, negative values provide animation tendency.

Positive weights (real) perform better than negative weights (animation).

比較了解LECO訓練法了之後將調整參數和學習率希望用較小的檔案和較少的權重達到更好的效果

可用權重在+2~-2,建議權重為+2~-1.0,正值提供真實的傾向,副值提供動漫畫的傾向

在正權重(真實)的表現比較負權重(動畫)好

LECO学習法を理解した後、より小さなファイルとより少ない重みでより良い結果を得るために、パラメータと学習率を調整します。

利用可能な重みは+2~-2、推奨される重みは+2~-1.0、正の値はリアル傾向、負の値はアニメーション傾向を提供する。

正のウェイト(リアル)は負のウェイト(アニメーション)よりも良いパフォーマンスを発揮します。

Ver tradução

Classificação e Avaliação

5.0 /5
0 classificação(ções)

Sem classificações ou avaliações suficientes

avatar
oosayam
123
3.3K
Anúncio
2024-04-01
Publicar Modelo
2023-09-21
Atualizar info do modelo
Detalhes do modelo
Tipo
LORA
Tempo de Publicação
2023-09-21
Modelo básico
SD 1.5
Introdução à Versão

After understanding the LECO training method, we will adjust the parameters and the learning rate in order to achieve better results with smaller files and less weights.

Available weights are +2~-2, recommended weights are +2~-1.0, positive values provide real tendency, negative values provide animation tendency.

Positive weights (real) perform better than negative weights (animation).

比較了解LECO訓練法了之後將調整參數和學習率希望用較小的檔案和較少的權重達到更好的效果

可用權重在+2~-2,建議權重為+2~-1.0,正值提供真實的傾向,副值提供動漫畫的傾向

在正權重(真實)的表現比較負權重(動畫)好

LECO学習法を理解した後、より小さなファイルとより少ない重みでより良い結果を得るために、パラメータと学習率を調整します。

利用可能な重みは+2~-2、推奨される重みは+2~-1.0、正の値はリアル傾向、負の値はアニメーション傾向を提供する。

正のウェイト(リアル)は負のウェイト(アニメーション)よりも良いパフォーマンスを発揮します。

Escopo da licença
Fonte: civitai

1. Os direitos dos modelos repostados pertencem aos criadores originais.

2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar

Escopo da licença de criação
Transmissão ao vivo
Fusão
Permitir download
Licença comercial
Imagens geradas podem ser vendidas ou usadas para fins comerciais
Permitir revenda de modelos ou sua venda após a combinação
QR Code
Baixar App SeaArt
Continue sua jornada de criação com IA no celular