Buckets:
| # JoyImageEditTransformer3DModel | |
| El modelo se puede cargar con el siguiente fragmento de código. | |
| ```python | |
| from diffusers import JoyImageEditTransformer3DModel | |
| transformer = JoyImageEditTransformer3DModel.from_pretrained("jdopensource/JoyAI-Image-Edit-Diffusers", subfolder="transformer", dtype=torch.bfloat16) | |
| ``` | |
| ## JoyImageEditTransformer3DModel[[diffusers.JoyImageEditTransformer3DModel]] | |
| #### diffusers.JoyImageEditTransformer3DModel[[diffusers.JoyImageEditTransformer3DModel]] | |
| ```python | |
| diffusers.JoyImageEditTransformer3DModel(patch_size: list = [1, 2, 2], in_channels: int = 16, out_channels: int | None = None, hidden_size: int = 3072, num_attention_heads: int = 24, text_dim: int = 4096, mlp_width_ratio: float = 4.0, num_layers: int = 20, rope_dim_list: list[int] = [16, 56, 56], rope_type: str = 'rope', theta: int = 256) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_joyimage.py#L372) | |
| Modelo JoyImage Transformer para la generación / edición de imágenes. | |
| Arquitectura DiT de doble flujo con embeddings de condicionamiento estilo WAN y embeddings de posición rotatoria personalizados. | |
| #### forward[[diffusers.JoyImageEditTransformer3DModel.forward]] | |
| ```python | |
| forward(hidden_states: Tensor, timestep: Tensor, encoder_hidden_states: Tensor = None, return_dict: bool = True) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_joyimage.py#L522) | |
| **Parámetros:** | |
| hidden_states (`torch.Tensor` de forma `(batch_size, num_channels, num_frames, height, width)` o `(batch_size, num_items, num_channels, num_frames, height, width)`) : `hidden_states` de entrada. | |
| timestep (`torch.LongTensor`) : Se utiliza para indicar el paso de desruido. | |
| encoder_hidden_states (`torch.Tensor`, *opcional*) : Embeddings condicionales (embeddings calculados a partir de las condiciones de entrada, como los prompts) a utilizar. | |
| return_dict (`bool`, *opcional*, valor predeterminado `True`) : Indica si se debe devolver un `~models.transformer_2d.Transformer2DModelOutput` en lugar de una tupla simple. | |
| **Devuelve:** | |
| Si `return_dict` es True, se devuelve un `~models.transformer_2d.Transformer2DModelOutput`, en caso contrario, una `tuple` donde el primer elemento es el tensor de la muestra. | |
| El método forward de [JoyImageEditTransformer3DModel](/docs/diffusers/main/es/api/models/transformer_joyimage#diffusers.JoyImageEditTransformer3DModel). | |
| ## 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) | |
| ``` | |
| [Fuente](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/modeling_outputs.py#L21) | |
| **Parámetros:** | |
| sample (`torch.Tensor` de forma `(batch_size, num_channels, height, width)` o `(batch size, num_vector_embeds - 1, num_latent_pixels)` si [Transformer2DModel](/docs/diffusers/main/es/api/models/transformer2d#diffusers.Transformer2DModel) es discreto): las salidas de estados ocultos condicionadas a la entrada `encoder_hidden_states`. Si es discreto, devuelve distribuciones de probabilidad para los píxeles latentes sin ruido. | |
| La salida de [Transformer2DModel](/docs/diffusers/main/es/api/models/transformer2d#diffusers.Transformer2DModel). | |
Xet Storage Details
- Size:
- 3.47 kB
- Xet hash:
- 4a9349516361aa0a08046b9a3584e95b2139f03d75ed8d381ca119d6629d6245
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.