Buckets:
| # AllegroTransformer3DModel | |
| Un modèle Diffusion Transformer pour des données 3D de [Allegro](https://github.com/rhymes-ai/Allegro) a été introduit dans [Allegro: Open the Black Box of Commercial-Level Video Generation Model](https://huggingface.co/papers/2410.15458) par RhymesAI. | |
| Le modèle peut être chargé à l'aide du fragment de code suivant. | |
| ```python | |
| from diffusers import AllegroTransformer3DModel | |
| transformer = AllegroTransformer3DModel.from_pretrained("rhymes-ai/Allegro", subfolder="transformer", dtype=torch.bfloat16).to("cuda") # or "mps", "xpu", "cpu" | |
| ``` | |
| ## AllegroTransformer3DModel[[diffusers.AllegroTransformer3DModel]] | |
| #### diffusers.AllegroTransformer3DModel[[diffusers.AllegroTransformer3DModel]] | |
| ```python | |
| diffusers.AllegroTransformer3DModel(patch_size: int = 2, patch_size_t: int = 1, num_attention_heads: int = 24, attention_head_dim: int = 96, in_channels: int = 4, out_channels: int = 4, num_layers: int = 32, dropout: float = 0.0, cross_attention_dim: int = 2304, attention_bias: bool = True, sample_height: int = 90, sample_width: int = 160, sample_frames: int = 22, activation_fn: str = 'gelu-approximate', norm_elementwise_affine: bool = False, norm_eps: float = 1e-06, caption_channels: int = 4096, interpolation_scale_h: float = 2.0, interpolation_scale_w: float = 2.0, interpolation_scale_t: float = 2.2) | |
| ``` | |
| [Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_allegro.py#L174) | |
| #### forward[[diffusers.AllegroTransformer3DModel.forward]] | |
| ```python | |
| forward(hidden_states: Tensor, encoder_hidden_states: Tensor, timestep: LongTensor, attention_mask: typing.Optional[torch.Tensor] = None, encoder_attention_mask: typing.Optional[torch.Tensor] = None, image_rotary_emb: tuple[torch.Tensor, torch.Tensor] | None = None, return_dict: bool = True) | |
| ``` | |
| [Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_allegro.py#L305) | |
| **Paramètres :** | |
| hidden_states (`torch.Tensor` de forme `(batch_size, num_channels, num_frames, height, width)`) : `hidden_states` d'entrée. | |
| encoder_hidden_states (`torch.Tensor` de forme `(batch_size, sequence_len, embed_dims)`) : Embeddings conditionnels (embeddings calculés à partir des conditions d'entrée telles que les prompts) à utiliser. | |
| timestep (`torch.LongTensor`) : Utilisé pour indiquer l'étape de débruitage. | |
| attention_mask (`torch.Tensor`, *facultatif*) : Masque d'auto-attention appliqué à `hidden_states`. | |
| encoder_attention_mask (`torch.Tensor`, *facultatif*) : Masque d'attention croisée appliqué à `encoder_hidden_states`. | |
| image_rotary_emb (`tuple` de `torch.Tensor`, *facultatif*) : Incrustations positionnelles rotatives précalculées. | |
| return_dict (`bool`, *facultatif*, par défaut `True`) : Indique s'il faut retourner un `~models.transformer_2d.Transformer2DModelOutput` plutôt qu'un simple tuple. | |
| **Retourne :** | |
| Si `return_dict` est True, un `~models.transformer_2d.Transformer2DModelOutput` est renvoyé, sinon un `tuple` dont le premier élément est le tenseur d'échantillon. | |
| La méthode forward du [AllegroTransformer3DModel](/docs/diffusers/main/fr/api/models/allegro_transformer3d#diffusers.AllegroTransformer3DModel). | |
| ## Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]] | |
| #### diffusers.models.modeling_outputs.Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]] | |
| ```python | |
| diffusers.models.modeling_outputs.Transformer2DModelOutput(sample: torch.Tensor) | |
| ``` | |
| [Source](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/modeling_outputs.py#L21) | |
| **Paramètres :** | |
| sample (`torch.Tensor` de forme `(batch_size, num_channels, height, width)` ou `(batch size, num_vector_embeds - 1, num_latent_pixels)` si [Transformer2DModel](/docs/diffusers/main/fr/api/models/transformer2d#diffusers.Transformer2DModel) est discret) : Les états cachés en sortie, conditionnés par l'entrée `encoder_hidden_states`. Si discret, renvoie les distributions de probabilité pour les pixels latents non bruités. | |
| La sortie de [Transformer2DModel](/docs/diffusers/main/fr/api/models/transformer2d#diffusers.Transformer2DModel). | |
Xet Storage Details
- Size:
- 4.24 kB
- Xet hash:
- f43704785cbcf132bc0213addab6dffeafed70e7b195338713b7f60d7657c9f8
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.