Buckets:
| # Capas de normalizaci贸n | |
| Capas de normalizaci贸n personalizadas para admitir varios modelos en 馃 Diffusers. | |
| ## AdaLayerNorm[[diffusers.models.normalization.AdaLayerNorm]] | |
| #### diffusers.models.normalization.AdaLayerNorm[[diffusers.models.normalization.AdaLayerNorm]] | |
| ```python | |
| diffusers.models.normalization.AdaLayerNorm(embedding_dim: int, num_embeddings: int | None = None, output_dim: int | None = None, norm_elementwise_affine: bool = False, norm_eps: float = 1e-05, chunk_dim: int = 0) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L27) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| num_embeddings (`int`, *opcional*) : El tama帽o del diccionario de embeddings. | |
| output_dim (`int`, *opcional*) -- | |
| norm_elementwise_affine (`bool`, por defecto `False) -- | |
| norm_eps (`bool`, por defecto `False`) -- | |
| chunk_dim (`int`, por defecto `0`) -- | |
| Capa de normalizaci贸n modificada para incorporar embeddings de paso de tiempo. | |
| ## AdaLayerNormZero[[diffusers.models.normalization.AdaLayerNormZero]] | |
| #### diffusers.models.normalization.AdaLayerNormZero[[diffusers.models.normalization.AdaLayerNormZero]] | |
| ```python | |
| diffusers.models.normalization.AdaLayerNormZero(embedding_dim: int, num_embeddings: int | None = None, norm_type = 'layer_norm', bias = True) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L130) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| num_embeddings (`int`) : El tama帽o del diccionario de embeddings. | |
| Capa de normalizaci贸n adaptativa: normalizaci贸n de capa cero adaptativa (adaLN-Zero). | |
| ## AdaLayerNormSingle[[diffusers.models.normalization.AdaLayerNormSingle]] | |
| #### diffusers.models.normalization.AdaLayerNormSingle[[diffusers.models.normalization.AdaLayerNormSingle]] | |
| ```python | |
| diffusers.models.normalization.AdaLayerNormSingle(embedding_dim: int, use_additional_conditions: bool = False) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L235) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| use_additional_conditions (`bool`) : Si se deben usar condiciones adicionales para la normalizaci贸n o no. | |
| Capa de normalizaci贸n adaptativa: normalizaci贸n de capa 煤nica adaptativa (adaLN-single). | |
| Como se propuso en PixArt-Alpha (ver: https://huggingface.co/papers/2310.00426; Secci贸n 2.3). | |
| ## AdaGroupNorm[[diffusers.models.normalization.AdaGroupNorm]] | |
| #### diffusers.models.normalization.AdaGroupNorm[[diffusers.models.normalization.AdaGroupNorm]] | |
| ```python | |
| diffusers.models.normalization.AdaGroupNorm(embedding_dim: int, out_dim: int, num_groups: int, act_fn: str | None = None, eps: float = 1e-05) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L269) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| num_embeddings (`int`) : El tama帽o del diccionario de embeddings. | |
| num_groups (`int`) : El n煤mero de grupos en los que separar los canales. | |
| act_fn (`str`, *opcional*, valor predeterminado `None`) : La funci贸n de activaci贸n a utilizar. | |
| eps (`float`, *opcional*, valor predeterminado `1e-5`) : El valor de epsilon a utilizar para la estabilidad num茅rica. | |
| Capa GroupNorm modificada para incorporar embeddings de paso de tiempo. | |
| ## AdaLayerNormContinuous[[diffusers.models.normalization.AdaLayerNormContinuous]] | |
| #### diffusers.models.normalization.AdaLayerNormContinuous[[diffusers.models.normalization.AdaLayerNormContinuous]] | |
| ```python | |
| diffusers.models.normalization.AdaLayerNormContinuous(embedding_dim: int, conditioning_embedding_dim: int, elementwise_affine = True, eps = 1e-05, bias = True, norm_type = 'layer_norm') | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L307) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : Dimensi贸n de embedding a utilizar durante la proyecci贸n. | |
| conditioning_embedding_dim (`int`) : Dimensi贸n de la condici贸n de entrada. | |
| elementwise_affine (`bool`, defaults to `True`) : Boolean flag to denote if affine transformation should be applied. | |
| eps (`float`, por defecto 1e-5) : Factor epsilon. | |
| bias (`bias`, por defecto `True`) : Bandera booleana para indicar si se debe usar sesgo. | |
| norm_type (`str`, por defecto `"layer_norm"`) : Capa de normalizaci贸n a utilizar. Valores admitidos: "layer_norm", "rms_norm". | |
| Capa de normalizaci贸n adaptativa con una capa de normalizaci贸n (layer_norm o rms_norm). | |
| ## RMSNorm[[diffusers.models.normalization.RMSNorm]] | |
| #### diffusers.models.normalization.RMSNorm[[diffusers.models.normalization.RMSNorm]] | |
| ```python | |
| diffusers.models.normalization.RMSNorm(dim, eps: float, elementwise_affine: bool = True, bias: bool = False) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L472) | |
| **Par谩metros:** | |
| dim (`int`) : N煤mero de dimensiones a usar para `weights`. Solo es efectivo cuando `elementwise_affine` es True. | |
| eps (`float`) : Valor peque帽o que se utiliza al calcular el rec铆proco de la ra铆z cuadrada. | |
| elementwise_affine (`bool`, defaults to `True`) : Boolean flag to denote if affine transformation should be applied. | |
| bias (`bool`, por defecto False) : Si tambi茅n se entrena el par谩metro `bias`. | |
| RMS Norm, tal como se introdujo en https://huggingface.co/papers/1910.07467 por Zhang et al. | |
| ## GlobalResponseNorm[[diffusers.models.normalization.GlobalResponseNorm]] | |
| #### diffusers.models.normalization.GlobalResponseNorm[[diffusers.models.normalization.GlobalResponseNorm]] | |
| ```python | |
| diffusers.models.normalization.GlobalResponseNorm(dim) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L563) | |
| **Par谩metros:** | |
| dim (`int`) : N煤mero de dimensiones a utilizar para `gamma` y `beta`. | |
| Normalizaci贸n de respuesta global, tal como se introdujo en ConvNeXt-v2 (https://huggingface.co/papers/2301.00808). | |
| ## LuminaLayerNormContinuous[[diffusers.models.normalization.LuminaLayerNormContinuous]] | |
| #### diffusers.models.normalization.LuminaLayerNormContinuous[[diffusers.models.normalization.LuminaLayerNormContinuous]] | |
| ```python | |
| diffusers.models.normalization.LuminaLayerNormContinuous(embedding_dim: int, conditioning_embedding_dim: int, elementwise_affine = True, eps = 1e-05, bias = True, norm_type = 'layer_norm', out_dim: int | None = None) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L354) | |
| ## SD35AdaLayerNormZeroX[[diffusers.models.normalization.SD35AdaLayerNormZeroX]] | |
| #### diffusers.models.normalization.SD35AdaLayerNormZeroX[[diffusers.models.normalization.SD35AdaLayerNormZeroX]] | |
| ```python | |
| diffusers.models.normalization.SD35AdaLayerNormZeroX(embedding_dim: int, norm_type: str = 'layer_norm', bias: bool = True) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L96) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| num_embeddings (`int`) : El tama帽o del diccionario de embeddings. | |
| Capa de normalizaci贸n adaptativa: normalizaci贸n adaptativa con cero (AdaLN-Zero). | |
| ## AdaLayerNormZeroSingle[[diffusers.models.normalization.AdaLayerNormZeroSingle]] | |
| #### diffusers.models.normalization.AdaLayerNormZeroSingle[[diffusers.models.normalization.AdaLayerNormZeroSingle]] | |
| ```python | |
| diffusers.models.normalization.AdaLayerNormZeroSingle(embedding_dim: int, norm_type = 'layer_norm', bias = True) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L173) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| num_embeddings (`int`) : El tama帽o del diccionario de embeddings. | |
| Capa de normalizaci贸n adaptativa: normalizaci贸n de capa cero adaptativa (adaLN-Zero). | |
| ## LuminaRMSNormZero[[diffusers.models.normalization.LuminaRMSNormZero]] | |
| #### diffusers.models.normalization.LuminaRMSNormZero[[diffusers.models.normalization.LuminaRMSNormZero]] | |
| ```python | |
| diffusers.models.normalization.LuminaRMSNormZero(embedding_dim: int, norm_eps: float, norm_elementwise_affine: bool) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L205) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| Capa de normalizaci贸n adaptativa RMS normalization zero. | |
| ## LpNorm[[diffusers.models.normalization.LpNorm]] | |
| #### diffusers.models.normalization.LpNorm[[diffusers.models.normalization.LpNorm]] | |
| ```python | |
| diffusers.models.normalization.LpNorm(p: int = 2, dim: int = -1, eps: float = 1e-12) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L583) | |
| ## CogView3PlusAdaLayerNormZeroTextImage[[diffusers.models.normalization.CogView3PlusAdaLayerNormZeroTextImage]] | |
| #### diffusers.models.normalization.CogView3PlusAdaLayerNormZeroTextImage[[diffusers.models.normalization.CogView3PlusAdaLayerNormZeroTextImage]] | |
| ```python | |
| diffusers.models.normalization.CogView3PlusAdaLayerNormZeroTextImage(embedding_dim: int, dim: int) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L403) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| num_embeddings (`int`) : El tama帽o del diccionario de embeddings. | |
| Capa de normalizaci贸n adaptativa: normalizaci贸n de capa cero adaptativa (adaLN-Zero). | |
| ## CogVideoXLayerNormZero[[diffusers.models.normalization.CogVideoXLayerNormZero]] | |
| #### diffusers.models.normalization.CogVideoXLayerNormZero[[diffusers.models.normalization.CogVideoXLayerNormZero]] | |
| ```python | |
| diffusers.models.normalization.CogVideoXLayerNormZero(conditioning_dim: int, embedding_dim: int, elementwise_affine: bool = True, eps: float = 1e-05, bias: bool = True) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L448) | |
| ## MochiRMSNormZero[[diffusers.models.transformers.transformer_mochi.MochiRMSNormZero]] | |
| #### diffusers.models.transformers.transformer_mochi.MochiRMSNormZero[[diffusers.models.transformers.transformer_mochi.MochiRMSNormZero]] | |
| ```python | |
| diffusers.models.transformers.transformer_mochi.MochiRMSNormZero(embedding_dim: int, hidden_dim: int, eps: float = 1e-05, elementwise_affine: bool = False) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/transformers/transformer_mochi.py#L88) | |
| **Par谩metros:** | |
| embedding_dim (`int`) : El tama帽o de cada vector de incrustaci贸n. | |
| Adaptive RMS Norm utilizado en Mochi. | |
| ## MochiRMSNorm[[diffusers.models.normalization.MochiRMSNorm]] | |
| #### diffusers.models.normalization.MochiRMSNorm[[diffusers.models.normalization.MochiRMSNorm]] | |
| ```python | |
| diffusers.models.normalization.MochiRMSNorm(dim, eps: float, elementwise_affine: bool = True) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/normalization.py#L535) | |
Xet Storage Details
- Size:
- 11.2 kB
- Xet hash:
- b892c96dd77e6f5cc673317051412ec4061ca14a1af6e85e36d7028da63e93a5
路
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.