You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: comfyui_embedded_docs/docs/EpsilonScaling/en.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](<https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon> Scaling/en.md)
1
+
> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/en.md)
2
2
3
3
Implements the Epsilon Scaling method from the research paper "Elucidating the Exposure Bias in Diffusion Models." This method improves sample quality by scaling the predicted noise during the sampling process. It uses a uniform schedule to mitigate exposure bias in diffusion models.
Copy file name to clipboardExpand all lines: comfyui_embedded_docs/docs/EpsilonScaling/es.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
> Esta documentación fue generada por IA. Si encuentra algún error o tiene sugerencias de mejora, ¡no dude en contribuir! [Editar en GitHub](<https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon> Scaling/es.md)
1
+
> Esta documentación fue generada por IA. Si encuentra algún error o tiene sugerencias de mejora, ¡no dude en contribuir! [Editar en GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/es.md)
2
2
3
3
Implementa el método Epsilon Scaling del artículo de investigación "Elucidating the Exposure Bias in Diffusion Models". Este método mejora la calidad de las muestras escalando el ruido predicho durante el proceso de muestreo. Utiliza un programa uniforme para mitigar el sesgo de exposición en los modelos de difusión.
Copy file name to clipboardExpand all lines: comfyui_embedded_docs/docs/EpsilonScaling/fr.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
> Cette documentation a été générée par IA. Si vous trouvez des erreurs ou avez des suggestions d'amélioration, n'hésitez pas à contribuer ! [Modifier sur GitHub](<https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon> Scaling/fr.md)
1
+
> Cette documentation a été générée par IA. Si vous trouvez des erreurs ou avez des suggestions d'amélioration, n'hésitez pas à contribuer ! [Modifier sur GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/fr.md)
2
2
3
3
Implémente la méthode Epsilon Scaling issue du document de recherche "Elucidating the Exposure Bias in Diffusion Models". Cette méthode améliore la qualité des échantillons en mettant à l'échelle le bruit prédit pendant le processus d'échantillonnage. Elle utilise un calendrier uniforme pour atténuer le biais d'exposition dans les modèles de diffusion.
Copy file name to clipboardExpand all lines: comfyui_embedded_docs/docs/EpsilonScaling/ja.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください! [GitHub で編集](<https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon> Scaling/ja.md)
1
+
> このドキュメントは AI によって生成されました。エラーを見つけた場合や改善のご提案がある場合は、ぜひ貢献してください! [GitHub で編集](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/ja.md)
2
2
3
3
Epsilon Scalingメソッドを、研究論文「Elucidating the Exposure Bias in Diffusion Models」に基づいて実装します。このメソッドは、サンプリングプロセス中に予測されたノイズをスケーリングすることで、サンプルの品質を向上させます。拡散モデルにおけるエクスポージャーバイアスを軽減するために、均一なスケジュールを使用します。
Copy file name to clipboardExpand all lines: comfyui_embedded_docs/docs/EpsilonScaling/ko.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](<https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon> Scaling/ko.md)
1
+
> 이 문서는 AI에 의해 생성되었습니다. 오류를 발견하거나 개선 제안이 있으시면 기여해 주세요! [GitHub에서 편집](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/ko.md)
2
2
3
3
"Epsilon Scaling" 연구 논문에서 제안된 방법을 구현합니다. 이 방법은 샘플링 과정에서 예측된 노이즈를 스케일링하여 샘플 품질을 향상시킵니다. 확산 모델의 노출 편향을 완화하기 위해 균일한 스케줄을 사용합니다.
Copy file name to clipboardExpand all lines: comfyui_embedded_docs/docs/EpsilonScaling/ru.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,4 +1,4 @@
1
-
> Эта документация была создана с помощью ИИ. Если вы обнаружите ошибки или у вас есть предложения по улучшению, пожалуйста, внесите свой вклад! [Редактировать на GitHub](<https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/Epsilon> Scaling/ru.md)
1
+
> Эта документация была создана с помощью ИИ. Если вы обнаружите ошибки или у вас есть предложения по улучшению, пожалуйста, внесите свой вклад! [Редактировать на GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/EpsilonScaling/ru.md)
2
2
3
3
Реализует метод масштабирования эпсилон из научной статьи "Elucidating the Exposure Bias in Diffusion Models". Этот метод улучшает качество сэмплов путём масштабирования предсказанного шума в процессе сэмплирования. Используется равномерный график для снижения bias экспозиции в диффузионных моделях.
0 commit comments