# JoyImageEditTransformer3DModel

Model dapat dimuat dengan potongan kode berikut.

```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)
```

[Sumber](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_joyimage.py#L372)

Model JoyImage Transformer untuk pembuatan / pengeditan gambar.

Arsitektur DiT dual-stream dengan embedding kondisioning bergaya WAN dan embedding posisi rotasi kustom.

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

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

[Sumber](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/transformers/transformer_joyimage.py#L522)

**Parameter:**

hidden_states (`torch.Tensor` dengan bentuk `(batch_size, num_channels, num_frames, height, width)` atau `(batch_size, num_items, num_channels, num_frames, height, width)`) : `hidden_states` masukan.

timestep (`torch.LongTensor`) : Digunakan untuk menunjukkan langkah denoising.

encoder_hidden_states (`torch.Tensor`, *opsional*) : Embedding kondisional (embedding yang dihitung dari kondisi input seperti prompt) yang akan digunakan.

return_dict (`bool`, *opsional*, defaultnya `True`) : Apakah akan mengembalikan `~models.transformer_2d.Transformer2DModelOutput` alih-alih tuple biasa.

**Mengembalikan:**

Jika `return_dict` bernilai True, sebuah `~models.transformer_2d.Transformer2DModelOutput` akan dikembalikan, selain itu sebuah `tuple` di mana elemen pertama adalah tensor sampel.

Metode forward dari [JoyImageEditTransformer3DModel](/docs/diffusers/main/id/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)
```

[Sumber](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/modeling_outputs.py#L21)

**Parameter:**

sample (`torch.Tensor` dengan bentuk `(batch_size, num_channels, height, width)` atau `(batch size, num_vector_embeds - 1, num_latent_pixels)` jika [Transformer2DModel](/docs/diffusers/main/id/api/models/transformer2d#diffusers.Transformer2DModel) bersifat diskrit) : Output hidden states yang dikondisikan pada input `encoder_hidden_states`. Jika diskrit, mengembalikan distribusi probabilitas untuk piksel laten yang tidak berisik.

Output dari [Transformer2DModel](/docs/diffusers/main/id/api/models/transformer2d#diffusers.Transformer2DModel).