# JoyImageEditTransformer3DModel

可以使用以下代码片段加载该模型。

```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)
```

[源代码](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/transformers/transformer_joyimage.py#L372)

用于图像生成/编辑的 JoyImage Transformer 模型。

采用 WAN 风格条件嵌入和自定义旋转位置嵌入的双流 DiT 架构。

#### forward[[diffusers.JoyImageEditTransformer3DModel.forward]]

```python
forward(hidden_states: Tensor, timestep: Tensor, encoder_hidden_states: Tensor = None, return_dict: bool = True)
```

[源代码](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/transformers/transformer_joyimage.py#L522)

**参数：**

hidden_states (`torch.Tensor`，形状为 `(batch_size, num_channels, num_frames, height, width)` 或 `(batch_size, num_items, num_channels, num_frames, height, width)`) : 输入 `hidden_states`。

timestep (`torch.LongTensor`)：用于指示去噪步骤。

encoder_hidden_states (`torch.Tensor`, *可选*) : 要使用的条件嵌入（根据输入条件（如提示词）计算得出的嵌入）。

return_dict (`bool`，*可选*，默认为 `True`)：是否返回 `~models.transformer_2d.Transformer2DModelOutput` 而不是普通元组。

**返回值：**

如果 `return_dict` 为 True，则返回 `~models.transformer_2d.Transformer2DModelOutput`，否则返回一个 `tuple`，其中第一个元素是样本张量。

[JoyImageEditTransformer3DModel](/docs/diffusers/v0.43.0/zh/api/models/transformer_joyimage#diffusers.JoyImageEditTransformer3DModel) 的前向方法。

## 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)
```

[源代码](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/modeling_outputs.py#L21)

**参数：**

sample (`torch.Tensor`，形状为 `(batch_size, num_channels, height, width)`；若 [Transformer2DModel](/docs/diffusers/v0.43.0/zh/api/models/transformer2d#diffusers.Transformer2DModel) 为离散模式，则为 `(batch size, num_vector_embeds - 1, num_latent_pixels)`)：以 `encoder_hidden_states` 输入为条件的隐藏状态输出。若为离散模式，则返回未加噪潜在像素的概率分布。

[Transformer2DModel](/docs/diffusers/v0.43.0/zh/api/models/transformer2d#diffusers.Transformer2DModel) 的输出。